Open source Models

BERT is a language model from Google that reads text in both directions and is pre-trained by filling in masked words. Fine-tuned per task, it set new records on question answering and language-understanding benchmarks and later went into Google Search.

RoseTTAFold is a three-track neural network for protein structure prediction, published by the Baker lab in 2021; its accuracy approached AlphaFold2's at CASP14, it models protein–protein complexes from sequence alone, and it is distributed as open code with a public web server.

An open-weight text-to-image model released publicly by Stability AI on 22 August 2022, built on latent diffusion and small enough to run on consumer GPUs, which made local image generation widely accessible.

A family of foundation language models from Meta AI, released in 7B to 65B parameter sizes and trained on public data; its 13B model was reported to beat GPT-3 on most benchmarks.

ESM3 is a protein generative model announced by EvolutionaryScale in June 2024 that reasons over sequence, structure and function together, and generated a fluorescent protein estimated to sit over 500 million years of evolution away from known ones.

Llama 3.1, released on 23 July 2024, added a 405-billion-parameter model to the Llama 3 family and extended its context to 128,000 tokens. Meta called the 405B the largest and most capable openly available foundation model.

DeepSeek-V3 is an open-weight mixture-of-experts language model that DeepSeek released in December 2024. Each token uses 37 billion of its 671 billion parameters, and DeepSeek describes its chat model as comparable to leading closed-source systems.

DeepSeek-R1 is an open-weight reasoning model that DeepSeek released on 20 January 2025. Built on DeepSeek-V3-Base and trained with reinforcement learning, it is released under the MIT License, which allows commercial use and distillation.

Isaac GR00T N1 is an open foundation model for humanoid robots that NVIDIA announced on 18 March 2025. It is designed to be post-trained for a specific robot or task, and it pairs a planning model with quick motion control.

Qwen3 is a family of large language models from Alibaba, released on 29 April 2025 under Apache 2.0. Its main feature is hybrid thinking, which lets one model reason step by step or answer directly.

Kimi K2 is an open-weight mixture-of-experts language model from Moonshot AI, released in July 2025 with 1 trillion total parameters, 32 billion active per token and a 128K-token context.

DeepSeek-V4, released in preview on 24 April 2026, comprises V4-Pro and V4-Flash, two open mixture-of-experts models with a 1M-token context. Its architecture targets long-context efficiency, and its later releases extended the series with agent upgrades and multimodal input.

Kimi K3 is a 2.8-trillion-parameter open-weight multimodal model from Moonshot AI, released on 16 July 2026 with weights following on 27 July under the Kimi K3 License.

K2 Horizon is a family of six open language models from the Institute of Foundation Models, released in September 2026 with weights, code, training data and recipes under the Apache 2.0 licence.

Jais-3-375B-A23B is an open-weight Arabic-focused mixture-of-experts model from the Institute of Foundation Models: 375 billion parameters stored, 23 billion active per token, a 512,000-token context window and Apache 2.0 weights.

GPT-1 was OpenAI's first generative pre-trained transformer, published in June 2018. It showed that one language model, pre-trained on unlabelled text and then fine-tuned, could improve results on many language tasks.

GPT-2 is a large language model that OpenAI announced in February 2019. Its largest version has 1.5 billion parameters. OpenAI first withheld the full model, then released it in stages through November 2019.

Baidu's first ERNIE pre-trained language model, released in March 2019, added entity- and phrase-level masking to BERT-style pre-training and reported state-of-the-art results on five Chinese NLP tasks.

T5 is a family of Google Transformer models that recasts every language task as text in, text out. Its 11-billion-parameter version set state of the art on several benchmarks, and the code, models and C4 dataset were released openly.

An image-text model from OpenAI that learns to match pictures with their captions. Trained on about 400 million image-caption pairs, it can classify images by comparing them against written prompts, with no task-specific training.

GPT-J-6B is a six-billion-parameter open language model released by EleutherAI in June 2021 under the Apache 2.0 license. Its published scores sit close to GPT-3 Curie, making it a widely used free baseline for large-model research.

GPT-NeoX-20B is a 20-billion-parameter open autoregressive language model released by EleutherAI in February 2022, with weights under Apache 2.0 and its training code, described by its makers as the largest publicly accessible general-purpose model of its kind at the time.

BLOOM is a 176-billion-parameter open multilingual language model released on 12 July 2022 by the BigScience project, with weights available under a responsible-use license.

Whisper is OpenAI's open-source speech recognition system, released in September 2022 and trained on 680,000 hours of audio, which transcribes speech in many languages and translates it into English.

GLM-130B is a 130-billion-parameter open bilingual Chinese–English dense language model from Tsinghua University's KEG group and Zhipu AI, built to give researchers an open model that matches GPT-3 at the hundred-billion scale.

An open bilingual chat model from Zhipu AI and Tsinghua KEG with about 6.2 billion parameters, small enough to run on one consumer GPU, with weights fully open for research.

The Segment Anything Model (SAM) is a promptable image segmentation model Meta AI released in April 2023. Given a point, a box or a mask, it outlines the object the prompt refers to.

Meta's family of open-weight language models released in July 2023 in 7B, 13B and 70B sizes, each with a dialogue-tuned Chat variant, issued under a custom licence that allowed free research and commercial use.

SDXL is Stability AI's open text-to-image diffusion model, announced in July 2023 with a 3.5B-parameter base model and a refiner stage, generating natively at 1024×1024. A distilled version, SDXL Turbo, cut generation down to a single step.

Qwen, known in Chinese as Tongyi Qianwen (通义千问), is Alibaba's family of large language models. Its first open-weight model, Qwen-7B, was released on 3 August 2023, and the family has grown through many later versions.

Code Llama is a family of coding models that Meta released in August 2023 by further training Llama 2 on code. It ranges from 7 billion to 70 billion parameters and uses the Llama 2 community license.

Baichuan 2 is the second-generation open model family from Baichuan, released on 6 September 2023 in 7B and 13B sizes. Commercial use required an application and was limited by user numbers.

Mistral AI's first model: a 7.3-billion-parameter language model released in September 2023 under the Apache 2.0 license, built to match much larger models on standard benchmarks.

Fuyu-8B is a decoder-only multimodal model that Adept open-sourced in October 2023; it drops the image encoder, accepts arbitrary resolutions, and reads screens and charts.

Yi-34B and Yi-6B are open bilingual base models from 01.AI, released in November 2023 and trained on 3 trillion tokens. Yi-34B ranked first among open pre-trained models at launch.

Grok-1 is xAI's first large language model, announced on 3 November 2023 as the engine of the Grok chatbot. Its 314-billion-parameter weights were released openly in March 2024.

An open-weight sparse mixture-of-experts language model from Mistral AI, released in December 2023: 46.7B total parameters but 12.9B used per token, a 32k-token context, and results above Llama 2 70B on most benchmarks.

OLMo is the Allen Institute for AI's open language model, released on 1 February 2024 in 1B and 7B sizes with its Dolma training data, training code, logs and checkpoints, all under Apache 2.0.

Gemma is a family of lightweight open language models from Google DeepMind, released in February 2024 in 2B and 7B sizes, built from the same research and technology as Gemini and offered for commercial use under Google's terms.

Stable Diffusion 3, announced by Stability AI on 22 February 2024, is a suite of 800 million to 8 billion parameter models that pairs a diffusion transformer with flow matching.

EvoLLM-JP is a Japanese model from Sakana AI built by evolutionarily searching merges of three open-source models instead of training from scratch; the 7B result has mathematics ability none of its sources had alone.

DBRX is Databricks' openly licensed large language model, a mixture-of-experts transformer with 132 billion total parameters and 36 billion active per token, announced on 27 March 2024.

Jamba, released by AI21 Labs on 28 March 2024, is an open-weights model that combines Mamba state-space layers with Transformer attention. It has 52 billion total parameters and a 256k-token context window.

Llama 3 is an open model family from Meta, released on 18 April 2024 at 8 billion and 70 billion parameters. It was pretrained on over 15 trillion tokens of publicly available data.

Phi-3 is Microsoft's family of small language models, launched in April 2024 with Phi-3-mini, a 3.8-billion-parameter model small enough to run on a phone.

Snowflake's open-weight model with 480 billion total and 17 billion active parameters, built as a dense-MoE hybrid, released in April 2024 under Apache 2.0 and trained for under 2 million dollars.

DeepSeek-V2 is a mixture-of-experts language model released in May 2024 with 236B total parameters, of which 21B are activated per token. It introduced Multi-head Latent Attention and used DeepSeekMoE for economical sparse training.

Qwen2 is the Qwen family's June 2024 generation, with five sizes from 0.5B to 72B parameters, context lengths up to 128K tokens, and most sizes released under Apache 2.0.

OpenVLA is a 7-billion-parameter open-source vision-language-action model trained on 970,000 real robot demonstrations, released with checkpoints and code so that other groups can fine-tune and run it on their own robots.

FLUX.1 is a family of 12-billion-parameter text-to-image models released by Black Forest Labs on 1 August 2024 in pro, dev and schnell variants. The dev version is open-weight, and the variants carry different licenses.

xAI's Grok-2 and Grok-2 mini, released in August 2024 as a beta for X subscribers, added image input, posted competitive benchmark scores and later had their weights published.

Qwen2.5 is the Qwen family's September 2024 generation. Its launch included 13 open-weight models, with up to 18 trillion pretraining tokens, 128K context and most models under Apache 2.0.

Llama 3.2, announced on 25 September 2024, added vision models at 11 billion and 90 billion parameters and small text-only models at 1 billion and 3 billion for edge and mobile devices.

Hunyuan-Large is Tencent's open-weight mixture-of-experts model, with 389 billion total parameters and 52 billion activated, released in November 2024 under a Tencent license.

HunyuanVideo is Tencent's open-source text-to-video generation model, with over 13 billion parameters, released in December 2024. Running it locally needs at least 60GB of GPU memory.

Phi-4 is Microsoft's 14-billion-parameter dense decoder-only language model, built with a data-quality-first recipe heavy on synthetic data and released with full weights under the MIT licence in January 2025.

MiniMax-01 is an open-weight model series released in January 2025. It includes the language model MiniMax-Text-01 and the vision-language model MiniMax-VL-01, and uses a hybrid attention design that supports very long context.

Step-Video-T2V is an open text-to-video model with 30 billion parameters. StepFun released its weights, code, a Turbo variant and a technical report under the MIT license on 17 February 2025.

Wan2.1 is Alibaba's open-source video generation model family, released on 25 February 2025 under Apache 2.0. It creates videos from text or images and can render Chinese and English text.

Ling is a family of open-weight Mixture-of-Experts language models from Ant Group's InclusionAI, released with a technical report arguing that a 300B-scale MoE can be trained without premium GPUs.

A 32-billion-parameter open-weight reasoning model released by the Qwen team on 6 March 2025, trained mainly through scaled reinforcement learning and reported to perform comparably to the much larger DeepSeek-R1.

Gemma 3 is Google's third generation of open Gemma models, released on 12 March 2025 in 1B to 27B sizes, with a 128,000-token context window, image input on the larger variants, and support for more than 140 languages at the pretrained level.

ERNIE 4.5 is Baidu's native multimodal foundation model, released on 16 March 2025 and handling text, images, audio and video. In June 2025 Baidu open-sourced ten models from the family under the Apache License 2.0.

Llama 4 Maverick is a mixture-of-experts model Meta released alongside Scout on 5 April 2025, with 400 billion total parameters and a 1-million-token context. Its ranking on LMArena was later questioned.

Llama 4 Scout is a mixture-of-experts model Meta released on 5 April 2025. It has 109 billion total parameters, 17 billion of them active for each token, and a context window of 10 million tokens.

MiMo-7B is a 7-billion-parameter reasoning model from Xiaomi's LLM-Core team, pre-trained on 25 trillion tokens and tuned with reinforcement learning on verifiable math and code problems, reported to surpass OpenAI o1-mini on several reasoning benchmarks.

Falcon-H1 is a family of open-weight language models that runs Transformer attention and state space layers in parallel, released in sizes from 0.5B to 34B parameters under the Falcon-LLM Licence.

An updated release of DeepSeek's open-weight reasoning model, published on 28 May 2025 under the MIT License, with markedly higher scores on competition math, science and coding benchmarks, plus system-prompt support and stronger function calling.

FLUX.1 Kontext is a family of image models from Black Forest Labs, announced on 29 May 2025, that generates and edits pictures from both text and image inputs. Its open-weight dev variant followed in June 2025.

MiniMax-M1 is an open reasoning model released by MiniMax in June 2025. It has 456B total parameters, a native 1-million-token context and an Apache 2.0 license, and it comes in 40K and 80K thinking-budget versions.

GLM-4.5 is Zhipu's open-weight language model, released in July 2025 with 355 billion total parameters and a lighter sibling, GLM-4.5-Air. Both are hybrid reasoning models released under the MIT License.

EXAONE 4.0 is LG's family of large language models, released as a 32B model and a 1.2B on-device model, merging chat usability with a reasoning mode and adding tool use and Spanish support.

A 14.74-billion-parameter Korean-English reasoning model released by NAVER in July 2025, built by compressing a larger model and training it with a four-stage reasoning recipe at a fraction of the cost of comparable models.

Qwen3-2507 is a staged 2025 refresh of the open-weight Qwen3 models that split thinking and non-thinking into separate checkpoints, raised native context to 262,144 tokens, and scored far above the original non-thinking mode on published benchmarks.

Qwen3-Coder is an open-weight family of coding models from the Qwen team; its flagship 480B-parameter model, announced in July 2025, was built and trained specifically for agentic coding tasks.

Step 3 is StepFun's open multimodal reasoning model, with 321 billion total parameters and 38 billion active per token. It was released in July 2025 and uses Apache 2.0.

gpt-oss is a family of open-weight reasoning language models released by OpenAI on 5 August 2025, in 120-billion and 20-billion parameter sizes, under the permissive Apache 2.0 license.

ByteDance Seed's open-weight 36-billion-parameter model family from August 2025, trained on 12 trillion tokens with a 512K-token context window and a user-settable thinking budget.

DeepSeek-V3.1, released on 21 August 2025 under the MIT License, was DeepSeek's first hybrid model, supporting both a thinking mode and a non-thinking mode in one set of weights. It has 671 billion total parameters, with 37 billion activated per token.

Qwen3-VL is Alibaba's open vision-language model family, released in September 2025 under Apache 2.0. Its 235B flagship handles long video, GUI operation and 2D and 3D grounding.

LongCat-Flash is a 560-billion-parameter Mixture-of-Experts language model from Meituan's LongCat team, which activates roughly 27 billion parameters per token and was released with open weights under the MIT license.

An open-source image generation model from Tencent that handles image understanding and generation inside a single autoregressive mixture-of-experts framework; its code, weights and technical report were released in September 2025.

MiniMax-M2 is an open-weights mixture-of-experts language model released by MiniMax in October 2025, with 230B total and 10B active parameters, aimed at coding and agentic workflows.

Kimi K2 Thinking is a reasoning model released by Moonshot AI in November 2025, built on the Kimi K2 mixture-of-experts architecture and trained for native INT4 inference and long chains of tool calls.

Olmo 3 is the third generation of the Allen Institute for AI's fully open language models, announced on 20 November 2025 in 7B and 32B dense Transformer sizes, with a 65,536-token context and all datasets openly available.

FLUX.2 is Black Forest Labs' image generation and editing model family, released on 25 November 2025, spanning hosted tiers and open-weight releases, with support for 4-megapixel output and up to 10 reference images.

DeepSeekMath-V2, released on 27 November 2025, is a mathematical reasoning model trained to verify its own proofs. DeepSeek reported gold-level scores on IMO 2025 and CMO 2024 problems, and 118 of 120 on Putnam 2024.

GLM-4.7 is Zhipu's open-weights language model released in December 2025, aimed at multilingual agentic coding and terminal tasks. It reports clear gains over GLM-4.6 on software-engineering benchmarks and ships under the MIT license.

DeepSeek-V3.2, released on 1 December 2025, succeeded the experimental V3.2-Exp and integrated thinking into tool use. Its companion V3.2-Speciale, which maximizes reasoning, reached gold-level results at several 2025 competitions.

Mistral AI's flagship model of the Mistral 3 family, released in December 2025: a sparse mixture-of-experts model with 675B total parameters, open weights under Apache 2.0, and image understanding.

Solar Open 100B is Upstage's open-weight mixture-of-experts language model for English and Korean, released in December 2025 with 102.6 billion total parameters, 12 billion active per token, and a custom licence.

Kimi K2.5 is a natively multimodal open-weight model from Moonshot AI, released on 27 January 2026. It has 1 trillion total parameters, a 256K-token context and an Agent Swarm feature for parallel sub-agents.

Step 3.5 Flash is an open-weights Mixture-of-Experts language model from StepFun, released in February 2026 with 196 billion total parameters, a 256K-token context and an Apache 2.0 license.

MiniMax-M2.5 is an open-weight 229B-parameter language model released in February 2026 for agentic coding and office work, shipped alongside a faster Lightning variant and reported at the top of software-engineering benchmarks.

GLM-5 is Zhipu's open model released on 12 February 2026 under the MIT License, with 744 billion parameters and 40 billion active. It was built for agentic engineering.

Qwen3.5 is a natively multimodal model family from Alibaba released in February 2026. Its open flagship, Qwen3.5-397B-A17B, has 397B total parameters and 17B active per token, under Apache 2.0.

Reka Edge is a 7-billion-parameter vision-language model from Reka AI, released on 11 March 2026, built to take images, video and text and to run locally on laptops, phones and small edge devices.

An open reasoning vision-language-action model from NVIDIA for humanoid robots, announced in March 2026 as commercially usable and trained on large public robot manipulation datasets.

A generation of Alibaba's Qwen models released in April 2026, spanning proprietary Plus and Max versions aimed at agentic coding and open-weight models such as Qwen3.6-35B-A3B, a 35B-parameter mixture-of-experts with 3B active parameters.

Gemma 4 is Google's fourth generation of open-weight models, released in April 2026 and built on the same research and technology as Gemini 3, ranging from phone-sized E2B and E4B to a 26B mixture-of-experts and a 31B dense model.

GLM-5.1 is Zhipu AI's open-source large language model released in April 2026, built for coding and long-running agent tasks and notable for topping SWE-Bench Pro ahead of competing frontier models in Zhipu's own comparison.

EXAONE 4.5 is LG AI Research's first open-weight vision language model: a 33-billion-parameter model with a 1.2-billion-parameter vision encoder, trained on documents and text, with a 256K-token context window, released in April 2026.

Laguna XS.2 is Poolside's first open-weight coding model: 33 billion total parameters with 3 billion active per token, released under Apache 2.0 and trained on 30 trillion tokens.

Command A+ is Cohere's open-source mixture-of-experts language model, released on 20 May 2026 under the Apache 2.0 licence with 218 billion total and 25 billion active parameters, aimed at sovereign and critical-infrastructure deployments.

MiniCPM5 is a series of small, dense, open-weight language models from the MiniCPM team, beginning with a 1B model released in May 2026 and followed by a 2B model in September 2026, all aimed at on-device and other resource-constrained deployment.

A mixture-of-experts language model released by MiniMax in June 2026, with about 428B total parameters, a 1M-token context window and a new sparse attention scheme built for long-context and agent-style work. [^1]

Zhipu's open-weight language model released in June 2026 under the MIT License, with a 1M-token context, a shared sparse-attention indexer, and higher reasoning and coding scores than GLM-5.1.

Tencent Hy3 is an open-weight reasoning model released on 6 July 2026 under Apache 2.0, with 295 billion total parameters, 21 billion active and a 256K context.

Inkling is the first model released by Thinking Machines Lab: a 975B-parameter mixture-of-experts model with open weights, native text, image and audio input, and a context window of up to 1M tokens.

Qwen3.8 is Alibaba's 2026 flagship line. Its open 2.4-trillion-parameter model, Qwen3.8-2.4T-A95B, released in August 2026, has 95B active parameters and a custom license.

GLM-5.3 is Zhipu's open-weight language model released on 14 August 2026. It keeps the GLM-5.2 base model and gains its improvements from post-training, with reported state-of-the-art open results on agentic coding and cybersecurity benchmarks.

Tencent Hy4 preview is an open-weight mixture-of-experts model released on 28 August 2026 with 770 billion total parameters, 49 billion active and a context of over one million tokens.

DeepSeek-V4.1-Flash, released on 10 September 2026 under the API name deepseek-flash, is a 552-billion-parameter multimodal mixture-of-experts model with a causal encoder-decoder design and a 1M-token context.

Kimi K3.1 Pro is Moonshot AI's October 2026 open-weights model, the first in the K3.1 series, built for financial research, 3D modeling and coding. It keeps K3's mixture-of-experts scale but swaps in sparse attention layers.

Kolibri-1 is Aleph Alpha's open-weight German–English mixture-of-experts model: 78.1 billion parameters with 3.46 billion active per token, a 1,048,576-token context window, and weights that fit on a single H200 or B200.

Mistral Large 4 is Mistral AI's flagship open-weight model, with about 1 trillion total parameters, a 1M-token context window and native multimodality. It was previewed on 6 October 2026, and an improved version's weights followed on 29 October 2026.

Jais-3-MoVA-36B-A4B is an Arabic-centric mixture-of-experts model from the Institute of Foundation Models: 36 billion parameters, 4 billion active per token, a 512,000-token context and a mixture-of-values attention scheme.

Jais-3-7B is a dense 7B Arabic-and-English model from the Institute of Foundation Models, with a 512,000-token context window, a single-GPU footprint of about 18 GB, and reasoning returned in a separate field.

Muse Spark Open is Meta's open-weight large language model, announced on 15 October 2026. With 816 billion total parameters, it is built for coding and agentic work, and its weights can be downloaded, unlike the closed Muse Spark that started the family.

LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: one 2.17-billion-parameter model that reads text, images, video and audio and answers in text or speech.

ERNIE 2.0 is Baidu's pre-trained language model framework, published in 2019, which builds pre-training tasks incrementally through continual multi-task learning and reported results above BERT and XLNet on English and Chinese benchmarks.

GPT-Neo is a family of open text-generation models released by EleutherAI in March 2021 at 125M, 1.3B and 2.7B parameters, built to replicate the GPT-3 architecture and distributed with freely downloadable weights under an MIT license.

OPT-175B is a 175-billion-parameter language model from Meta AI, announced in May 2022. Meta said it was the first model of its size released with both pretrained weights and the code to train and use them.

Galactica is a large language model for science, unveiled by Meta AI and Papers with Code in November 2022. Its public demo was taken down about three days later, after users found it produced fake papers.

Stable Diffusion 2 is an open-source text-to-image model family released by Stability AI on 24 November 2022, built on a new OpenCLIP text encoder and shipped with upscaling, depth-guided and inpainting models; version 2.1 followed weeks later.

Pythia is a suite of 16 open language models from EleutherAI, ranging from 70 million to 12 billion parameters, all trained on the same data in the same order, with 154 public checkpoints from each training run.

Stable LM is Stability AI's family of open language models, first released in April 2023 as 3B- and 7B-parameter alpha versions under licenses that allow commercial use of the base models and research-only use of the instruction-tuned ones.

StarCoder is an open-access code language model of about 15.5 billion parameters, released on 4 May 2023 by the BigCode project led by Hugging Face and ServiceNow.

Baichuan-7B is an open-source, 7-billion-parameter language model for Chinese and English released in June 2023, the first model from Baichuan, trained on about 1.2 trillion tokens and evaluated on Chinese and English benchmarks.

Phi-1 is a 1.3-billion-parameter Transformer language model for Python from Microsoft Research, which showed that filtered and synthetic "textbook quality" training data can partly substitute for model and data scale.

An open-source 13-billion-parameter language model from Baichuan, released in Base and Chat versions in July 2023, trained on 1.4 trillion tokens and benchmarked against Meta's LLaMA-13B.

Qwen-VL is a family of vision-language models released in August 2023 that builds on the Qwen language model to caption images, answer questions about them, locate objects and read text, with open Base and Chat versions.

Phi-1.5 is a 1.3-billion-parameter language model from Microsoft Research, trained on curated synthetic "textbook" text rather than web crawls; its report claims natural-language performance comparable to models five times larger.

PLaMo-13B is a 13-billion-parameter, LLaMA-based language model from Preferred Networks, pre-trained on English and Japanese open data and released on Hugging Face in September 2023 under the Apache-2.0 licence.

DeepSeek's first model release: a family of open-source code models from 1.3B to 33B parameters, trained from scratch on 2 trillion tokens and reported to beat Codex and GPT-3.5 on several benchmarks.

GraphCast is a Google DeepMind machine-learning model that makes global weather forecasts up to 10 days ahead, producing a 10-day forecast in under a minute on a single TPU and outperforming ECMWF's HRES on most tested variables.

Stable Video Diffusion is Stability AI's image-to-video model, released on 21 November 2023 as a research preview that turns a single still image into a clip of a few seconds.

DeepSeek LLM is DeepSeek's first general-purpose language model series, released on 29 November 2023 in 7B and 67B sizes, each with a base version and a chat version.

Phi-2 is a 2.7-billion-parameter base language model from Microsoft Research, announced on 12 December 2023. Microsoft reported that it matched or beat models up to 25 times larger on complex benchmarks, making it a reference point for small-model training.

DeepSeekMoE is a mixture-of-experts architecture from DeepSeek, released in January 2024, that splits experts finely and keeps a few shared experts always active so that each expert holds focused knowledge. Its 16B open-weights model matched larger dense models at a fraction of the computation.

AlphaGeometry is a Google DeepMind system that pairs a neural language model with a symbolic deduction engine to solve olympiad geometry problems, reaching near gold-medal level on a benchmark of 30 problems.

Yi-VL-34B and Yi-VL-6B are open vision-language models from 01.AI, released on 23 January 2024. They read images and text together and ranked first among open models on the MMMU and CMMMU benchmarks.

Aya 101 is a 13-billion-parameter, instruction-tuned language model from Cohere For AI that follows instructions in 101 languages. It was released under Apache 2.0 in February 2024.

DeepSeekMath is a 7B-parameter open language model built for mathematical reasoning and released in 2024. It reached 51.7% on the competition-level MATH benchmark without external tools, and introduced GRPO, a reinforcement-learning algorithm that uses less memory than PPO.

Qwen1.5 is the Qwen family's open model release of February 2024, with base and chat models from 0.5B to 72B parameters, later extended to 110B, and a mixture-of-experts model.

StarCoder2 is a family of open code models in 3B, 7B and 15B sizes, released in February 2024 by BigCode (Hugging Face and ServiceNow) with NVIDIA and trained on The Stack v2, published together with its dataset and training code.

Mengzi3 is an open-source large language model series from Langboat, released in 8B and 13B sizes under Apache-2.0, built on the Llama architecture and trained further on trillions of multilingual tokens.

A sparse mixture-of-experts language model from Mistral AI, released in April 2024 under the Apache 2.0 licence with 141 billion total parameters, of which 39 billion are active per token.

OpenELM is a family of small open language models from Apple, published in four sizes from 270M to 3B parameters with its training framework, logs, checkpoints and MLX conversion code.

Octo is an open-source generalist robot policy: a transformer-based diffusion model trained on 800,000 robot trajectories that can drive a range of robots out of the box and be fine-tuned to new setups.

Yi-1.5 is an open-source family of language models from 01.AI, released in 34B, 9B and 6B sizes in base and chat forms, built by continuing to pre-train the earlier Yi models on a large new corpus.

Hunyuan-DiT is Tencent's open text-to-image diffusion transformer, built for fine-grained English and Chinese prompt understanding. Its 2024 report and weights were released publicly, and human evaluations placed it ahead of several open models but behind leading closed ones.

Aya 23 is a family of open-weight multilingual instruction-tuned models from Cohere For AI, released in 8-billion and 35-billion-parameter sizes in May 2024. It covers 23 languages and was reported to outperform Aya 101 and several contemporary open models.

Nemotron-4 340B is a family of open models from NVIDIA, released on 14 June 2024 as base, instruct and reward models. It was built to generate synthetic data for training other language models, and it fits on a single eight-GPU DGX H100.

An open-source mixture-of-experts code model from DeepSeek, released in June 2024, that widened language coverage and context length over its predecessor and reported benchmark results above several closed models.

Google's second-generation Gemma open models, announced on 27 June 2024 in 9-billion and 27-billion-parameter sizes, using grouped-query attention, an 8,192-token context window and a license permitting commercial use.

Kolors is Kuaishou's open-weight text-to-image model, released on 6 July 2024, built on latent diffusion and tuned for both Chinese and English prompts.

SmolLM is a family of small language models with 135M, 360M and 1.7B parameters, released openly by Hugging Face in July 2024 for on-device use and trained on a purpose-built corpus of generated textbooks, code and filtered web text.

Mistral NeMo is a 12-billion-parameter language model released by Mistral AI with NVIDIA in July 2024, notable for a 128K-token context window, a new multilingual tokenizer called Tekken, and an Apache 2.0 release.

SAM 2 is Meta's 2024 successor to the Segment Anything Model. It segments objects in both images and videos in real time, and its release included the SA-V video dataset.

Phi-3.5 is Microsoft's August 2024 update to its small Phi models, released in three versions — mini, vision and the line's first mixture-of-experts model — under the MIT licence.

CogVideoX is an open-source family of text-to-video models from Zhipu AI and Tsinghua University, released starting in August 2024 and derived from the earlier open-source CogVideo.

EXAONE 3.0 7.8B is the first openly released model in LG AI Research's EXAONE family: an instruction-tuned model strong in Korean, published with gated weights on Hugging Face.

Jamba 1.5 is AI21 Labs' family of instruction-tuned language models, Mini and Large, which combine Transformer and Mamba layers, offer a 256,000-token effective context and ship with open weights.

Qwen2-VL is Alibaba's vision-language model released on 29 August 2024. It understands videos longer than 20 minutes, reads text in many languages, and can act as an agent on phones and robots.

OLMoE is a fully open sparse mixture-of-experts language model from Ai2: 7 billion total parameters, 1 billion active per token, pretrained on 5 trillion tokens, with weights, data, code and logs released.

DeepSeek-V2.5 is a model released on 5 September 2024 that merged DeepSeek's chat and code models into one, keeping both conversational and coding ability while improving safety scores.

Yi-Coder is a family of open-source code models from 01.AI, released in September 2024 in 1.5B and 9B sizes, each with base and chat versions, covering 52 programming languages with context up to 128K tokens.

Pixtral 12B is Mistral AI's first multimodal model, pairing a 12B language decoder with a 400M vision encoder. Released openly under Apache 2.0 in September 2024, it reads images at native resolution and was retired at the end of 2025.

Molmo is a family of open vision-language models released by Ai2 on 25 September 2024 that can point at objects in images, with weights, code, data and evaluations published openly.

Aya Expanse is a family of multilingual open-weight language models released by Cohere For AI in October 2024 in 8B and 32B sizes, covering 23 languages.

A family of text-to-image models from Stability AI, announced in October 2024: the 8.1-billion-parameter Large, a 4-step Turbo variant and the 2.5-billion-parameter Medium, released under a community licence.

SmolLM2 is Hugging Face's second family of small language models, released in November 2024 at 135M, 360M and 1.7B parameters, with open weights and a data-centric training recipe.

Tülu 3 is Ai2's open post-training recipe and model family, released in 8B and 70B sizes on top of Llama 3.1 and combining instruction tuning, preference tuning with on-policy data, and reinforcement learning with verifiable rewards.

OLMo 2 is the second generation of the Allen Institute for AI's fully open language model family, released in 7B and 13B sizes with weights, data, code and training recipes all public.

QwQ-32B-Preview is an experimental reasoning research model released by the Qwen team on 28 November 2024, with 32B parameters, a 32K-token context and open Apache 2.0 weights. It scored strongly on maths benchmarks but the team documented clear failure modes.

A family of three instruction-tuned Korean–English language models released by LG AI Research in December 2024, ranging from 2.4B to 32B parameters, with 32K-token context and weights out under a research-use licence.

Llama 3.3 70B is a text-only, instruction-tuned model Meta released on 6 December 2024. Meta said it performs close to the 405B Llama 3.1 at much lower cost and can run on a typical developer workstation.

A family of open mixture-of-experts vision-language models from DeepSeek, released in three sizes from 1.0B to 4.5B activated parameters for document, chart and OCR understanding, succeeding DeepSeek-VL.

Falcon3 is TII's family of open-weight language models from 1B to 10B parameters, released in base and instruct form; the 10B instruct model appeared on Hugging Face in December 2024 with a 32K context and a custom licence.

An open-weights 3-billion-parameter language model from Infinigence AI, released on Hugging Face in December 2024 under Apache-2.0, built on a Llama-2 architecture with a 32K-token context for local deployment.

Megrez-3B-Omni is an open-source model from December 2024 that understands images, text and audio on end-side devices, pairing a 2.29B-parameter language backbone with SigLip and Whisper encoders for about 4B parameters in total.

Qwen2.5-VL is Alibaba's vision-language model family released in January 2025 in 3B, 7B, 32B and 72B sizes. It reads charts and documents, localises objects, works as a visual agent and understands videos over an hour long.

NVIDIA Cosmos is a platform of world foundation models that generate physics-based video to train robots and autonomous vehicles, released as open-weight models in January 2025.

UI-TARS is a GUI agent model from ByteDance Seed: it takes only screenshots as input and outputs keyboard and mouse actions, reported state-of-the-art results on more than 10 benchmarks, and was released with open weights under Apache-2.0.

Hunyuan3D 2.0 is Tencent's large-scale system for generating high-resolution textured 3D assets: a shape diffusion transformer plus a texture model, released with code and pretrained models on 21 January 2025 alongside its technical report.

Baichuan-M1 is Baichuan's medical model line, released on 24 January 2025 with Baichuan-M1-preview and the open Baichuan-M1-14B, which Baichuan described as trained from scratch for medicine.

Janus-Pro is DeepSeek's January 2025 multimodal model that handles both image understanding and text-to-image generation in one system, released in 1B and 7B sizes as a stronger successor to Janus.

Mistral Small 3 is a 24-billion-parameter open-weight language model from Mistral AI, released in January 2025 under Apache 2.0 and tuned for low-latency inference on a single GPU or laptop.

Step-Audio is an open family of speech-interaction models released by StepFun on 17 February 2025. It includes Step-Audio-Chat, with 130 billion parameters, and Step-Audio-TTS-3B.

Phi-4-mini is a 3.8B-parameter text model and Phi-4-multimodal a 5.6B model that adds images and speech, both released by Microsoft in February 2025 as the small, efficiency-focused members of the Phi-4 family.

AI21 Labs' March 2025 hybrid SSM-Transformer instruction-following models, released as Jamba Large 1.6 and Jamba Mini 1.6 with 256k-token context, gated open weights and benchmarks AI21 compared against Mistral Large 2, Llama 3.3 70B and Command R+.

Cohere's first vision-language model, released in March 2025 as open-weight 8B and 32B versions. It handles images and text in 23 languages and, in Cohere's comparisons, beats several much larger models, under a non-commercial licence.

Reka Flash 3 is a 21-billion-parameter general-purpose reasoning model from Reka, trained from scratch and released with open weights under the Apache 2.0 licence on 11 March 2025.

The largest model in Ai2's OLMo 2 family: a 32-billion-parameter language model released with its data, code, weights and training details, and reported to outperform GPT-3.5-Turbo and GPT-4o mini on academic benchmarks.

Mistral Small 3.1 is an open-weight model released by Mistral AI in March 2025 that adds image understanding and a 128K-token context window to the Small line, runs on a single consumer GPU, and was later superseded by newer Small releases.

Llama Nemotron is NVIDIA's family of open reasoning models in Nano, Super and Ultra sizes, launched in March 2025 and built on Meta's Llama 3 models.

DeepSeek-V3-0324 is a March 2025 update to DeepSeek-V3 that keeps the same model structure while raising benchmark scores and moving to the MIT License.

Qwen2.5-Omni is Alibaba's end-to-end multimodal model that takes text, images, audio and video as input and answers with text and natural speech. The 7B version was released on 26 March 2025.

Kimi-VL is an open-source vision-language model from Moonshot AI, released in April 2025. It pairs a 16B-parameter mixture-of-experts language model with a native-resolution vision encoder, so only about 3B parameters are active at a time.

xLAM-2 is Salesforce's family of large action models, from 1 billion to 70 billion parameters, trained on simulated agent–human data and tuned for multi-turn tool use rather than single-call function calling.

ByteDance Seed's GUI agent model from April 2025 and the successor to UI-TARS. Its 7B version is open-source under Apache-2.0, and the family reports state-of-the-art results on several screen-control benchmarks.

An open image-editing model from StepFun released in April 2025 under Apache 2.0, pairing a multimodal language model with a diffusion image decoder and shipping weights, inference code and the GEdit-Bench evaluation set.

DeepSeek's open-source model for formal theorem proving in Lean 4, trained with a subgoal-decomposition pipeline; it reached an 88.9% pass ratio on MiniF2F-test and introduced the ProverBench benchmark.

A 14-billion-parameter open-weight reasoning model released by Microsoft in April 2025, built by fine-tuning Phi-4 on reasoning traces generated by OpenAI's o3-mini and published under the MIT licence.

Seed-Coder is a family of open code models released by ByteDance Seed in May 2025, with 8B-parameter Base, Instruct and Reasoning variants trained on data filtered by language models rather than hand-written rules.

Devstral is Mistral AI's family of open-weight models for agentic coding, first released in May 2025 with All Hands AI; the first version scored 46.8% on SWE-Bench Verified and could run on a single consumer GPU.

Sarvam-M is Sarvam AI's open-weights 24-billion-parameter model, post-trained from Mistral Small for eleven Indian languages. It runs in think and non-think modes and reports large gains on Indic, maths and coding benchmarks.

MiniCPM4 is a language model built for end-side devices rather than servers, pairing a trainable sparse attention mechanism with a compact data recipe and an inference stack tuned for long-context speed.

Magistral is Mistral AI's first family of reasoning models, launched in June 2025 with an open-weight Small model and an enterprise Medium model. It supports multilingual reasoning and was later updated and retired.

Gemma 3n is a mobile-first open model in Google's Gemma family, released in June 2025 in two sizes that run in roughly 2–3 GB of memory and natively accept image, audio, video and text input.

Hunyuan-A13B is Tencent's open-weight mixture-of-experts language model, released on 27 June 2025 with 80 billion total parameters, 13 billion active per token and a 256K context.

Jamba 1.7 is a July 2025 update to the Jamba family, with Large and Mini versions offering 256k-token context, nine languages, and improved grounding and steerability.

SmolLM3 is a 3-billion-parameter open model released by Hugging Face on 8 July 2025. It supports six languages and up to 128K tokens of context, with switchable reasoning, under Apache 2.0.

Voxtral is Mistral AI's family of speech-understanding models, released on 15 July 2025 in 24B and 3B sizes under Apache 2.0; it transcribes long audio, answers questions about it, and turns spoken requests into function calls.

Megrez2-3x7B-A3B is a mixture-of-experts language model from Infinigence AI built for on-device deployment, in which groups of adjacent layers share one pool of experts so that it stores 7.5 billion parameters but activates only 3 billion per token.

Step-Audio 2 is a speech model from StepFun that can understand audio and hold spoken conversations. Its mini versions were released under the Apache 2.0 license in 2025.

HunyuanWorld 1.0 is Tencent's open-source model for generating explorable, mesh-exportable 3D worlds from text or images. Released in July 2025, it was followed by a series of lighter and faster versions.

An open family of video generation models released in July 2025 under the Apache 2.0 licence, notable for bringing a two-expert mixture-of-experts design to video diffusion and for a 5B model that runs on a single consumer GPU.

Baichuan-M2 is an open-source medical-enhanced model with 32 billion parameters, built on Qwen2.5-32B and released under Apache 2.0 for research and reference.

A 20-billion-parameter open-weights image generation model released by Qwen in August 2025, notable for rendering text inside images, especially Chinese.

A vision-language model released by Zhipu on 11 August 2025, built on GLM-4.5-Air and covering image, video, long-document and GUI tasks; Zhipu reports state-of-the-art results at its scale on 42 benchmarks.

Qwen3-Omni is an open-weight multimodal model released by the Qwen team in September 2025 under Apache 2.0, able to take in text, audio and video and to answer in text or speech across many languages.

Qwen3-Next is an open-weight model from Alibaba's Qwen team, released in September 2025 under Apache 2.0. It has 80B total parameters, only 3B active per token, and a hybrid attention design later used in Qwen3.5.

GLM-4.6 is an open-weights large language model released by Zhipu in late September 2025, with a 200K-token context window, about 357 billion parameters and an MIT licence, aimed at coding, reasoning and agent work.

A 1.7-billion-parameter English model from Writer, fine-tuned from Qwen2.5-1.5B and released under Apache 2.0 with a 131,072-token context window, presented around grade-school mathematics.

A deep-thinking mixture-of-experts model from Baidu with 21 billion total and 3 billion active parameters, a 128K context window and an Apache 2.0 license, open-sourced in September 2025 alongside ERNIE X1.1.

A 1.7-billion-parameter reasoning model released by Writer in September 2025, fine-tuned from Nvidia's OpenReasoning-Nemotron-1.5B, with strong competition-mathematics scores and an Apache 2.0 licence.

An experimental DeepSeek model released on 29 September 2025 that introduced DeepSeek Sparse Attention to make long-context training and inference cheaper, shipped with open weights and an immediate API price cut.

A 3-billion-parameter open reasoning model from AI21 Labs, released under the Apache 2.0 licence with a hybrid Transformer-Mamba design, a 256k-token context window and local execution on phones, Macs and PCs.

DeepSeek-OCR is an open-source model of about 3B parameters that renders long text as 2D images and reads it back from a small number of vision tokens, testing whether optical compression can stand in for very long text contexts.

Baidu's open-weight multimodal reasoning model from November 2025: 28B total parameters with 3B active per token, "Thinking with Images" zoom-and-tool reasoning, and Apache 2.0 weights.

SAM 3 is Meta's segmentation model from November 2025. It finds, segments and tracks every instance of a concept named by a short text prompt or an example image, and Meta reported it doubles the accuracy of existing systems on this task.

MiniMax-M2.1 is an open-weight language model released in December 2025 as the successor to M2, aimed at software engineering and multilingual coding, with a 229B-parameter checkpoint and large reported gains on coding benchmarks.

Three small dense models from Mistral AI — 3B, 8B and 14B — released in December 2025 under Apache 2.0, each in base, instruct and reasoning variants with image understanding.

Devstral 2 is Mistral AI's 123B-parameter agentic coding model, released in December 2025 alongside the Mistral Vibe CLI and scoring 72.2% on SWE-bench Verified. It was deprecated in May 2026 and retired that July, replaced by Mistral Medium 3.5.

Molmo 2 is the second generation of Ai2's open vision-language models, released on 11 December 2025, which extends the Molmo line from still images to video with pointing, tracking and timestamped answers.

NVIDIA Nemotron 3 is an open family of hybrid mixture-of-experts language models, announced in December 2025 in Nano, Super and Ultra sizes, with up to one million tokens of context.

Baichuan-M3 is a new-generation open-source medical-enhanced language model with 235 billion parameters, built on Qwen3-235B-A22B and released under Apache 2.0 in January 2026.

MiniMax-M2.7 is a 229B-parameter language model released by MiniMax in March 2026, built for agentic work and presented by the company as its first model to take part in its own improvement.

Phi-4-reasoning-vision-15B is Microsoft's 15-billion-parameter open-weight vision-language model, released on 4 March 2026 under the MIT licence, built to switch between step-by-step reasoning for math and science and direct answers for image perception tasks.

Ai2's fully open 7B model, which mixes Transformer attention with Gated DeltaNet linear recurrent layers and matches its predecessor's MMLU accuracy using 49% fewer training tokens.

Mistral Small 4 is an open-weight mixture-of-experts model released in March 2026 that folds instruction-following, step-by-step reasoning and agentic coding into one model, with a switch that controls how much reasoning it does.

Kimi K2.6 is an open-weight Moonshot AI model released in April 2026, focused on long-horizon coding, with a 262,144-token context, text and image input, and Agent Swarm scaled to 300 sub-agents.

SenseNova U1 is SenseTime's open-weight multimodal model family, first released in April 2026 under Apache 2.0, which understands and generates images without a separate visual encoder or VAE.

A 128B-parameter open-weights multimodal model from Mistral AI, listed in April 2026 for agentic and coding work, briefly the default in Le Chat before being superseded by Mistral Large 4.

Stability AI's 2026 audio generation family: three open-weight models and a hosted flagship, able to generate and edit music and sound effects up to about six minutes long.

Step 3.7 Flash is a StepFun open-weights model released on 29 May 2026. It adds native image input to Step 3.5 Flash, supports a 256K context, and is licensed under Apache 2.0.

SenseNova U1.5 is SenseTime's open-weight, 8-billion-parameter model that handles image understanding, reasoning and native 4K generation in a single network, without separate vision encoders or VAEs. It is released under the Apache License 2.0.

Granite 4.2 is IBM's open-weight model generation, released on 25 August 2026 in 3B, 8B and 30B dense sizes, with a reasoning-capable 8B model under the permissive Apache-2.0 licence.

MiniMax-M3.1-Flash is a sparse mixture-of-experts model from MiniMax with about 428B total parameters, 23B activated per token, text, image and video input and up to 1M tokens of context, released on Hugging Face in October 2026.

PLaMo 3 Translate is a family of translation-specialised language models from Preferred Networks, released in four sizes from 0.8B to 31B parameters, covering 53 languages and shipping in several quantised formats.

Nemotron 3.5 Transcribe is Nvidia's free, open-weight speech transcription model, released on 28 October 2026. It handles recordings up to an hour long, transcribes up to 40 languages and can separate up to eight speakers.

ERNIE 5.5 Flash Base is Baidu's openly published base checkpoint from November 2026: a text-only sparse mixture-of-experts model with 280B total and 14B activated parameters, released for fine-tuning rather than as a finished assistant.

Codestral Mamba is a 7B open code model from Mistral AI, released in July 2024, that swaps the Transformer for the Mamba state-space architecture to get linear-time inference.

A 7-billion-parameter model released by Mistral AI on 16 July 2024 for mathematical and STEM reasoning, built on Mistral 7B, openly licensed, and now listed as deprecated.

NVLM is a family of multimodal large language models from NVIDIA, described in a paper posted to arXiv in September 2024; its flagship NVLM-D-72B was later released as open weights for non-commercial use.

NVIDIA's Llama-3.1-Nemotron-70B-Instruct is a version of Meta's Llama-3.1-70B-Instruct tuned with reinforcement learning from human feedback to give more helpful answers; on release it topped three automatic alignment benchmarks.

Nemotron Nano 2 is NVIDIA's 9B reasoning model, built on a hybrid Mamba-Transformer design and released with open weights and most of its training data; NVIDIA reports much higher throughput than similar-sized models.

Voxtral TTS is Mistral AI's first text-to-speech model, released in March 2026: about 4B parameters, nine languages, cloning from a three-second clip, open weights for non-commercial use and an API priced per character.