Compute

Microsoft's Maia 200 is an inference accelerator introduced on 26 January 2026, built on TSMC's 3-nanometer process with 216 GB of HBM3e memory and more than 10 petaflops at FP4, aimed at serving models such as OpenAI's GPT-5.2.

Large language modelsEnterpriseHardware & compute

NVIDIA Rubin is NVIDIA’s six-chip AI platform and the successor to Blackwell, announced at CES 2026. It targets lower-cost AI token generation, with partner products and cloud instances scheduled for 2026.

Large language modelsHardware & computeData & datasets

Cambricon's flagship MLU 690, in mass production since early 2026, is a dual-die accelerator with 196 GB of HBM3 memory and more than 700 TFLOPS of FP16 compute, aimed at very large-scale training workloads.

ChinaEnterpriseDeep learning

The AMD Instinct MI400 is AMD's next-generation data-center GPU for AI, expected in 2026 with 432 GB of HBM4 memory, and designed to be deployed inside AMD's Helios rack-scale system.

Large language modelsHardware & computeData & datasets

AWS Trainium3 is AWS's first 3-nanometer AI chip, delivering 2.52 petaflops of FP8 compute per chip and scaling to 144 chips in a Trn3 UltraServer, available through Amazon EC2 from December 2025.[^1][^2]

ReasoningHardware & computeData & datasets

Huawei's Ascend 970 is a planned AI chip announced in September 2025 as the last entry on the company's published roadmap, targeted for the fourth quarter of 2028 with roughly double the compute and wider interconnect and memory bandwidth than the Ascend 960.

ChinaEnterpriseDeep learning

The Ascend 960 is a Huawei AI chip on the company's three-year roadmap, slated for the fourth quarter of 2027 with twice the compute, memory and interconnect ports of the Ascend 950 and support for Huawei's HiF4 4-bit format.

ChinaEnterpriseDeep learning

Huawei's Ascend 950 is a two-chip AI series announced in September 2025, pairing a shared die with Huawei's own high bandwidth memory, up to 2 PFLOPS in low precision formats and 2 TB/s interconnect.

ChinaEnterpriseDeep learning

AMD's data-center GPU for AI, introduced in June 2025 on the CDNA 4 architecture, with 288 GB of HBM3E memory and very high low-precision throughput aimed at generative AI inference, positioned against Nvidia's Blackwell generation.

Large language modelsEnterpriseHardware & compute

AMD Instinct MI350X is a data-center GPU in AMD's MI350 series, built on the CDNA 4 architecture with up to 288 GB of HBM3E memory, up to 8 TB/s of bandwidth and a 1,000 W board power.

Large language modelsEnterpriseHardware & compute

SK hynix said on 19 March 2025 that it was the first to supply 12-layer HBM4 samples, a stack offering more than 2 TB of data per second and 36 GB of capacity, over 60% faster than HBM3E.

EnterpriseDeep learningHardware & compute

A rack-scale NVIDIA system announced in March 2025 that links 72 Blackwell Ultra GPUs and 36 Grace CPUs into one unit, rated at 1.5 times the AI performance of GB200 NVL72.

EnterpriseReasoningHardware & compute

Falcon Shores is an Intel chip that the company said in January 2025 it would use only as an internal test chip, never bringing it to market, while pointing to Jaguar Shores as its route into rack-scale AI data-centre systems.

Large language modelsProduct historyHardware & compute

Moore Threads' flagship training-and-inference GPU card, built on the PH100 chip and the Pinghu architecture, rated at 1,000 TFLOPS of dense AI compute with 80 GB of memory, and the company's main shipping product in 2025.

ChinaEnterpriseDeep learning

Hygon's Shengsuan No. 3 is a GPGPU-architecture deep computing processor that reached the market in 2025, built on a 7 nm chiplet design with 1.8 TB/s of HBM bandwidth and a CUDA-like software stack.

ChinaEnterpriseDeep learning

Huawei CloudMatrix384 is a Huawei Cloud service instance built on Atlas 900 A3 SuperPoDs, each linking up to 384 Ascend 910C chips so that they work as one computer.

ChinaEnterpriseDeep learning

Huawei's Ascend 910C is a data-center AI chip in the 910 series, built on the Da Vinci architecture. It reached the market in the first quarter of 2025 with 800 TFLOPS of FP16 compute and 128 GB of HBM.

ChinaEnterpriseDeep learning

TPU7x (Ironwood) is Google's seventh-generation TPU: 192 GB of high-bandwidth memory per chip, FP8 matrix units, 9,216 chips per pod, and a programming model that exposes two devices per chip.

Deep learningReasoningHardware & compute

AWS Trainium2 is Amazon Web Services' second-generation machine-learning chip, sold through 16-chip EC2 Trn2 instances and 64-chip Trn2 UltraServers, and pitched by AWS as offering better price performance than comparable GPU instances.

Large language modelsHardware & computeData & datasets

Google TPU v6e, also called Trillium, is a Google Cloud AI accelerator whose published specifications cover per-chip BF16 and FP8 compute, high-bandwidth HBM, and pod-scale interconnects for large training jobs.

Deep learningHardware & computeData & datasets

A data-center GPU announced by AMD on 10 October 2024, built on third-generation CDNA with 256 GB of HBM3E memory at 6 TB/s and aimed at models with a trillion parameters.

Large language modelsHardware & computeData & datasets

SK hynix's 12-layer HBM3E, announced in mass production on 26 September 2024, was the first 12-die high-bandwidth memory stack: 36 GB in a package no thicker than the eight-layer version, running at 9.6 Gbps.

EnterpriseDeep learningHardware & compute

Meta's second-generation in-house AI chip, published on 10 April 2024, built on TSMC's 5-nanometer process and aimed at the ranking and recommendation models Meta runs in its own data centers.

EnterpriseDeep learningHardware & compute

NVIDIA's GB200 NVL72 is a liquid-cooled rack that links 72 Blackwell GPUs and 36 Grace CPUs into a single NVLink domain aimed at trillion-parameter AI. Announced at GTC in March 2024, it is the building block of NVIDIA's Blackwell-generation DGX SuperPOD.

Large language modelsEnterpriseHardware & compute

NVIDIA's data-center GPU for the Blackwell generation, announced in March 2024 as the successor to Hopper, built from two joined dies and paired with NVLink and FP4 support for large-scale AI training and inference.

Large language modelsFoundation modelsHardware & compute

Cerebras's third-generation wafer-scale AI chip, announced in March 2024: 4 trillion transistors on one 46,225-square-millimetre piece of silicon, built to keep very large models in a single memory space.

Large language modelsDeep learningHardware & compute

Intel Gaudi 3 is an AI accelerator introduced in 2024, built from two 5 nm compute dies with 128 GB of HBM2e and 1,835 TFLOPS of BF16 and FP8 matrix throughput, plus integrated 200GbE networking on its OAM module.

EnterpriseDeep learningHardware & compute

Google TPU v5p is a 2023 TPU generation with 459 teraflops of peak BF16 and FP8 compute per chip, 95 GiB of HBM, and 8,960 chips per pod.

Deep learningHardware & computeData & datasets

Azure Maia 100 is Microsoft's first custom AI chip, announced in November 2023 and built to train and run large language models inside its own Azure data centres rather than being sold.

Large language modelsHardware & computeData & datasets

NVIDIA's H200, announced in November 2023, is a data center GPU that was the first to use HBM3e memory, offering 141 GB at 4.8 TB/s — nearly double the A100's capacity — and roughly double the H100's inference speed on Llama 2 70B.

Large language modelsEnterpriseHardware & compute

MTIA v1 is Meta's first-generation in-house AI inference accelerator, built on TSMC's 7 nm process with 128 MB of on-chip memory and designed for deep learning recommendation models.

EnterpriseDeep learningHardware & compute

Huawei's Ascend 910B is a 2023 volume-production AI chip rated at 320 TFLOPS of FP16, with 32 GB of HBM2e memory, 1.6 TB/s of bandwidth and a 310 W envelope on a 7-nanometer domestic process.

ChinaDeep learningHardware & compute

NVIDIA's China-specific data-center GPU, built to stay inside US export controls. Cut down from the H100 in core count and performance, it was still the most advanced NVIDIA chip legally sold in China until April 2025.

ChinaEnterpriseDeep learning

Cambricon's MLU 590 is a 7 nm cloud AI chip released in 2023 for both training and inference on models with hundreds of billions of parameters, and the centrepiece of the company's fifth-generation MLUarch line.

ChinaEnterpriseDeep learning

Biren's general-purpose GPU, released in August 2022, packages two dies on a 7 nm process with 77 billion transistors; the company claimed PFLOPS-level single-chip compute, a first for a Chinese firm.

ChinaEnterpriseDeep learning

NVIDIA's fourth-generation DGX system, announced in March 2022, packs eight H100 GPUs linked by NVLink plus BlueField-3 networking, and is rated at 32 petaflops of FP8 AI performance for enterprise AI infrastructure.

Large language modelsEnterpriseHardware & compute

NVIDIA's A800 is a data-center GPU that went into production in 2022 as a China-market alternative to the A100, with a reduced chip-to-chip transfer rate to meet US export-control thresholds.

ChinaEnterpriseDeep learning

AMD's data-center GPU accelerator launched on 8 November 2021, built on the CDNA 2 architecture with 220 compute units, 128 GB of HBM2e memory, and strong double-precision throughput alongside low-precision AI formats.

EnterpriseDeep learningHardware & compute

Cambricon's third-generation cloud AI chip, released in 2021: a 7 nm chiplet design with two compute dies, 256 TOPS at INT8, LPDDR5 memory and multi-chip interconnect, positioned for cost-effective inference.

ChinaEnterpriseDeep learning

NVIDIA's third-generation DGX system, unveiled on 14 May 2020: eight A100 GPUs, 320 GB of GPU memory, five petaflops of rated AI performance, and the ability to split into as many as 56 instances.

EnterpriseDeep learningHardware & compute

Google's TPU v4 is a machine-learning chip and supercomputer deployed since 2020, built into 4,096-chip pods with optically reconfigurable networking; PaLM and Gemini models were trained on it.

Large language modelsFoundation modelsHardware & compute

NVIDIA's DGX-2, announced in March 2018, packed 16 Tesla V100 GPUs and a new NVSwitch interconnect into one server that NVIDIA described as the first to reach two petaflops for deep learning.

Deep learningProduct historyHardware & compute

Google's third-generation Tensor Processing Unit, introduced in 2018, with doubled HBM capacity, higher peak throughput, lower power draw and liquid cooling for denser pods.

EnterpriseDeep learningHardware & compute

Google TPU v2 is the second-generation Tensor Processing Unit announced in May 2017. It added floating-point support and the bfloat16 format, and scaled to 256-chip pods rated at 11.5 petaFLOPS.

EnterpriseDeep learningHardware & compute

The NVIDIA Tesla P40 is a data-center GPU accelerator described in a September 2016 NVIDIA datasheet. Built on the Pascal architecture and aimed at deep learning inference, it pairs 24 GB of memory with 47 TOPS of INT8 throughput in a 250 W PCIe card.

Deep learningProduct historyHardware & compute

NVIDIA's DGX-1, unveiled in April 2016, packed eight Tesla P100 GPUs into a single chassis and was billed as the world's first deep learning supercomputer, turning accelerator count into one purchasable machine.

Deep learningProduct historyHardware & compute

NVIDIA's Tesla K80 is a dual-GPU data-center accelerator announced in November 2014, putting two GK210 chips, 24 GB of memory and up to 8.74 teraflops of single-precision performance on one 300 W board.

Research historyDeep learningHardware & compute

The Xicloud C600 is a MetaX data-center GPU built on the company's own GPGPU architecture, offering very large ECC-protected memory, MetaXLink scaling up to 128-GPU supernodes, a 1,000 W OAM 2.0 module, and air or liquid cooling.

Large language modelsChinaHardware & compute

Blackhole is Tenstorrent's AI accelerator chip; Galaxy Blackhole is a server holding 32 of them, rated at 23 PFLOPS of block FP8, with Ethernet links wiring chips and clusters together.

Large language modelsOpen sourceHardware & compute

SambaNova SN40L is an AI chip that SambaNova calls a Reconfigurable Dataflow Unit, pairing dataflow-style parallel execution with a three-tier memory system spanning on-chip SRAM, co-packaged HBM and DDR DRAM.

Large language modelsEnterpriseHardware & compute

GroqChip is Groq's AI processor, built for fully deterministic execution with no run-to-run variation. It pairs a 14-nanometer die with 230 MB of on-die SRAM, up to 750 INT8 TOPS and RealScale chip-to-chip links, and ships both as a chip and on the PCIe GroqCard.

Large language modelsHardware & computeData & datasets

Cerebras's second-generation wafer-scale chip, presented as the largest AI processor ever made: 2.6 trillion transistors, 850,000 cores and 40 GB of on-wafer memory on a single wafer built on a 7-nanometer process.

Deep learningProduct historyHardware & compute

NVIDIA's DGX Spark is a desktop-sized AI computer built on the GB10 Grace Blackwell Superchip, pairing a 20-core Arm CPU with a Blackwell GPU and up to 128 GB of unified memory for running large models locally.

Consumer appsHardware & computeData & datasets

A data-center GPU on NVIDIA's Ampere architecture, aimed at AI inference and mainstream enterprise workloads, with 24 GB of HBM2 memory, a 165 W power ceiling and the ability to split into as many as four MIG instances.

EnterpriseDeep learningHardware & compute

The NVIDIA A10 is a data-center GPU built on the Ampere architecture that combines graphics, video and AI inference in a single-slot PCIe card with 24 GB of memory, aimed at mainstream enterprise servers.

EnterpriseDeep learningHardware & compute

The NVIDIA Tesla T4 is a 70-watt, single-slot GPU built on the Turing architecture and aimed at AI inference, pairing Tensor Cores with dedicated video transcoding engines in a card that slots into ordinary servers.

Deep learningProduct historyHardware & compute

AWS Trainium is a chip built by Amazon Web Services for deep learning training, sold through EC2 Trn1 instances that AWS says cut training costs by up to 50% compared with comparable instances.

EnterpriseDeep learningHardware & compute