Hardware / NVIDIA /A100 80GB SXM

NVIDIA · GPU

A100 80GB SXM

Runs 154 models fully in memory, 9 more with CPU offload. 4 of those sit close enough to 80 GB that our size estimate is what decides them.

Memory

80 GB

Bandwidth

2039 GB/s

Runs

154

01

Specifications

Memory

80 GB

Decides which models fit at all.

Memory bandwidth

2039 GB/s

How fast it can read the model. Sets the speed of the reply.

Compute

312 TFLOPS

Trillions of half-precision sums a second. Sets how fast it reads a long prompt, not how fast it replies.

Power draw

400 W

At full load, for sizing a power supply.

MSRP

$15,000

What the maker asked for it new. We hold no used or street prices, so this is not what one costs today.

Released

Nov 16, 2020

Architecture

Ampere

02

What it runs

Best quant per model. Text models first, then speech, then what does not fit.

What is quantisation? →

ModelParamsContextSpeedVerdict

Granite 4.1 8B8.8B131K175 tok/sFits in memory Qwen3.6 35B A3B36B262K762 tok/sFits in memory Gemma 4 26B A4B25.8B131K487 tok/sFits in memory Qwen3.5-9B9.7B262K158 tok/sFits in memory Nemotron 3 Nano 30B A3B31.6B262K762 tok/sFits in memory Ministral 3 14B 251213.9B262K194 tok/sFits in memory Ministral 3 8B 25128.9B262K258 tok/sFits in memory Ministral 3 3B 25123.8B131K404 tok/sFits in memory gpt-oss-safeguard-20b21.5B131K542 tok/sFits in memory Granite 4.0 Micro3.2B66K717 tok/sFits in memory Qwen3 VL 8B Thinking8.8B131K306 tok/sFits in memory Qwen3 VL 30B A3B Thinking31.1B262K762 tok/sFits in memory Qwen3 Next 80B A3B Thinking81.3B131K650 tok/sFits in memory UI-TARS 7B8.3B66K276 tok/sFits in memory Hunyuan A13B Instruct80.4B131K176 tok/sFits in memory Llama Guard 4 12B12B262K191 tok/sFits in memory Qwen3 14B14.8B131K182 tok/sFits in memory Gemma 3 12B12.2B131K221 tok/sFits in memory Rocinante 12B12.2B66K126 tok/sFits in memory Llama 3.2 3B Instruct3.2B131K480 tok/sFits in memory Mistral Nemo12.2B131K221 tok/sFits in memory Qwen3.5-35B-A3B36B262K762 tok/sFits in memory Qwen3 VL 8B Instruct8.8B262K261 tok/sFits in memory Qwen3 VL 30B A3B Instruct31.1B262K762 tok/sFits in memory Qwen3 Next 80B A3B Instruct81.3B131K762 tok/sFits in memory Qwen3 30B A3B Thinking 250730.5B66K435 tok/sFits in memory Qwen3 Coder 30B A3B Instruct30.5B262K435 tok/sFits in memory Qwen3 30B A3B Instruct 250730.5B262K762 tok/sFits in memory Qwen3 8B8.2B131K328 tok/sFits in memory Gemma 3 4B4.3B131K533 tok/sFits in memory Reka Flash 320.9B66K129 tok/sFits in memory Llama 3.1 8B Instruct8B131K336 tok/sFits in memory Granite 4.2 8B8.8B131K175 tok/sFits in memory Nemotron 3.5 Content Safety4.3B131K533 tok/sFits in memory Cydonia 24B V4.123.6B131K114 tok/sFits in memory Uncensored24B66K112 tok/sFits in memory Mistral Small 3.2 24B24B131K112 tok/sFits in memory Mistral Small 3.1 24B24B66K112 tok/sFits in memory Gemma 3n 4B7.8B33K294 tok/sFits in memory UnslopNemo 12B12.2B33K188 tok/sFits in memory Llama 3.2 1B Instruct1.2B33K2242 tok/sFits in memory Qwen2.5 7B Instruct7.6B33K202 tok/sFits in memory Mistral Small 323.6B33K114 tok/sFits in memory Gemma 3 27B27.4B262K98 tok/sFits in memory Ternary Bonsai 2 27B27B262K100 tok/sFits in memory Reka Edge7.1B16K216 tok/sFits in memory Qwen3.5-27B27.8B131K97 tok/sFits in memory GLM 4.5 Air111B16K191 tok/sFits in memoryest Phi 414.7B16K183 tok/sFits in memory Qwen3.6 27B27.8B131K97 tok/sFits in memory Qwen3.8 27B27.8B131K97 tok/sFits in memory Muse Glimmer 30B29.8B131K90 tok/sFits in memory Voxtral Small 24B 250724.3B16K111 tok/sFits in memory Olmo 3 32B Think32.2B66K84 tok/sFits in memory Llama 3 8B Lunaris8B8K287 tok/sFits in memory MythoMax 13B13B8K176 tok/sFits in memory Qwen3 32B32.8B131K82 tok/sFits in memory Hy-MT2-1.8B2B8K1144 tok/sFits in memory Hy-MT2-30B-A3B30.1B8K650 tok/sFits in memory Hy-MT2-7B8B8K244 tok/sFits in memory Qwen3 VL 32B Instruct33.4B131K81 tok/sFits in memory Gemma 4 31B31.3B33K86 tok/sFits in memory GLM 4.7 Flash31.2B131K73 tok/sFits in memory Qwen2.5 Coder 32B Instruct32.8B33K82 tok/sFits in memory ReMM SLERP 13B13B4K207 tok/sFits in memory Nemotron 3.5 Lightning31.6B262K72 tok/sFits in memory Laguna XS 2.133.4B262K69 tok/sFits in memory Nex-N2-Mini35.1B262K65 tok/sFits in memory Gemma 2 27B27.2B8K99 tok/sFits in memory Nex-N2.5-Mini35.1B262K65 tok/sFits in memory Skyfall 36B V236.9B33K73 tok/sFits in memory Hermes 4 70B70.6B66K38 tok/sFits in memory Llama 3.3 Euryale 70B70.6B66K38 tok/sFits in memory Llama 3.1 Euryale 70B v2.270.6B66K38 tok/sFits in memory Hermes 3 70B Instruct70.6B66K38 tok/sFits in memory Llama 3.1 70B Instruct70.6B131K38 tok/sFits in memory Llama 3.3 70B Instruct70.6B131K38 tok/sFits in memory Qwen2.5 VL 72B Instruct73.4B66K37 tok/sFits in memory Qwen3 Coder Next79.7B131K29 tok/sFits in memory Qwen2.5 72B Instruct72.7B33K37 tok/sFits in memory Magnum v4 72B72.7B16K37 tok/sFits in memory Llama 4 Scout109B33K25 tok/sFits in memoryest GLM 4.6V108B33K21 tok/sFits in memory GLM 4.5V108B33K21 tok/sFits in memory R1 Distill Llama 70B70.6B8K38 tok/sFits in memory Command A111B16K24 tok/sFits in memoryest Ling-2.6-flash107B8K21 tok/sFits in memoryest

Speech models it runs67 modelsTranscription and speech models that fit in memory. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.

Niagara 19m Batch.en20M134532 tok/sFits in memory Niagara 38m Batch.en38M40401 tok/sFits in memory Higgs Audio v3 8b STT v28.9B302 tok/sFits in memory Higgs Audio v3 STT2.7B569 tok/sFits in memory Cohere Transcribe 03 20262.1B731 tok/sFits in memory Distil Large v3.50.8B1919 tok/sFits in memory Lite Whisper Large v3 Acc1.4B1638 tok/sFits in memory Owsm CTC v3.1 1B1.1B2446 tok/sFits in memory Owsm CTC v3.2 ft 1B1B1535 tok/sFits in memory Owsm CTC v4 1B1B2691 tok/sFits in memory Hubert Large Ls960 ft0.3B4798 tok/sFits in memory MMS 1b All1B2293 tok/sFits in memory Wav2vec2 Large 960h Lv60 Self0.3B4798 tok/sFits in memory Hojo ASR V15.2B443 tok/sFits in memory Granite 4.0 1b Speech2.3B668 tok/sFits in memory Granite Speech 3.3 2b3B897 tok/sFits in memory Granite Speech 3.3 8b8.6B313 tok/sFits in memory Granite Speech 4.1 2b2.3B1170 tok/sFits in memory Granite Speech 4.1 2b NAR2.3B1170 tok/sFits in memory STT 2.6b en2.6B1035 tok/sFits in memory Phi 4 Multimodal Instruct5.6B131K481 tok/sFits in memory VibeVoice ASR HF8.3B185 tok/sFits in memory Voxtral Mini 3B 25074.7B327 tok/sFits in memory Voxtral Mini 4B Realtime 26024.4B349 tok/sFits in memory Canary 180m Flash0.2B12741 tok/sFits in memory Canary 1b1B1535 tok/sFits in memory Canary 1b Flash0.8B1919 tok/sFits in memory Canary 1b v21B1535 tok/sFits in memory Canary Qwen 2.5b2.6B591 tok/sFits in memory Nemotron 3.5 ASR Streaming 0.6b0.6B2559 tok/sFits in memory Nemotron Speech Streaming en 0.6b0.6B2559 tok/sFits in memory Parakeet CTC 0.6b0.6B4484 tok/sFits in memory Parakeet CTC 1.1b1.1B1396 tok/sFits in memory Parakeet RNNT 0.6b0.6B2559 tok/sFits in memory Parakeet RNNT 1.1b1.1B2446 tok/sFits in memory Parakeet TDT CTC 110m0.1B13957 tok/sFits in memory Parakeet TDT 0.6b v20.6B3822 tok/sFits in memory Parakeet TDT 0.6b v30.6B2559 tok/sFits in memory Parakeet TDT 1.1b1.1B1396 tok/sFits in memory Nyra Health CrisperWhisper1.6B960 tok/sFits in memory Whisper Large v31.5B1529 tok/sFits in memory Whisper Large v3 Turbo0.8B3363 tok/sFits in memory MOSS Transcribe Diarize0.9B1706 tok/sFits in memory Qwen3 ASR 0.6B0.9B2990 tok/sFits in memory Qwen3 ASR 0.6B HF0.8B3363 tok/sFits in memory Qwen3 ASR 1.7B2.3B997 tok/sFits in memory Qwen3 ASR 1.7B HF2B768 tok/sFits in memory Zipformer cr CTC Transducer XL 290M0.3B7908 tok/sFits in memory Zipformer Transducer XL 290M0.3B5294 tok/sFits in memory ASR Conformer Largescaleasr0.5B5606 tok/sFits in memory GLM ASR Nano 25122.3B997 tok/sFits in memory Granite Speech 5.0 470m Turboctc0.5B4587 tok/sFits in memory Granite Speech 5.0 470m Turboctc nc0.5B5381 tok/sFits in memory Fun ASR Nano 2512 HF0.8B3363 tok/sFits in memory Gemma 4 12B it12B191 tok/sFits in memory Gemma 4 E2B it5.1B450 tok/sFits in memory Gemma 4 E4B it8B131K192 tok/sFits in memory Niagara 9m Batch.en9M170583 tok/sFits in memory Niagara 84m Batch.en84M32031 tok/sFits in memory ARK ASR 0.6B1.3B33K1764 tok/sFits in memory ARK ASR 3B4.1B33K656 tok/sFits in memory Audio8 ASR 0.1B0.3B33K5118 tok/sFits in memory MOSS Transcribe Preview 2B2.4B33K1121 tok/sFits in memory Moonshine Streaming Medium0.3B4K8969 tok/sFits in memory Moonshine Streaming Small0.1B4K15353 tok/sFits in memory Moonshine Streaming Tiny0B4Kno speed estimateFits in memory Moonshine Tiny0B194no speed estimateFits in memory

Runs only by spilling into system memory9 modelsThese load, but part of the weights sits in ordinary system memory, which is far slower than the chip.

Laguna S 2.1118B—no speed estimateSpills to system RAM Mistral Medium 3.5128B—no speed estimateSpills to system RAM Mistral Small 4119B—no speed estimateSpills to system RAM Nemotron 3 Super124B—no speed estimateSpills to system RAM Qwen3.5-122B-A10B125B—no speed estimateSpills to system RAM Devstral 2 2512125B—no speed estimateSpills to system RAM gpt-oss-120b120B—no speed estimateSpills to system RAM Mixtral 8x22B Instruct141B—no speed estimateSpills to system RAMest Ling-3.0-flash128B—no speed estimateSpills to system RAMest

Too large for this device61 modelsThe weights do not fit even with part of them offloaded to system memory. Closest calls first.

Step 3.7 Flash201B—no speed estimateToo large Step 3.5 Flash199B—no speed estimateToo large MiniMax M2.5229B—no speed estimateToo large Qwen3 235B A22B Thinking 2507235B—no speed estimateToo large Qwen3 VL 235B A22B Thinking236B—no speed estimateToo large Qwen3 VL 235B A22B Instruct236B—no speed estimateToo large DeepSeek V4 Flash291B—no speed estimateToo large Hy3299B—no speed estimateToo large GLM 5.3 Flash321B—no speed estimateToo large GLM 4.5358B—no speed estimateToo large Laguna M.1226B—no speed estimateToo large Nex-N2-Pro397B—no speed estimateToo large Nex-N2.5-Pro397B—no speed estimateToo large Trinity Large Thinking399B—no speed estimateToo large MiniMax M2.7229B—no speed estimateToo large MiniMax M2.1229B—no speed estimateToo large MiniMax M2229B—no speed estimateToo large Llama 4 Maverick402B—no speed estimateToo large Qwen3 235B A22B Instruct 2507235B—no speed estimateToo large GLM 4.6357B—no speed estimateToo large GLM 4.7358B—no speed estimateToo large ERNIE 4.5 VL 424B A47B424B—no speed estimateToo large Inkling Small266B—no speed estimateToo large MiniMax M3427B—no speed estimateToo large Hy3 preview299B—no speed estimateToo large DeepSeek V4 Flash Vision Exp305B—no speed estimateToo large MiniMax M1456B—no speed estimateToo large MiMo-V2.5311B—no speed estimateToo large Nemotron 3 Ultra561B—no speed estimateToo large Qwen3 Coder 480B A35B480B—no speed estimateToo large R1 0528685B—no speed estimateToo large DeepSeek V3 0324685B—no speed estimateToo large DeepSeek V3.1685B—no speed estimateToo large Jamba Large 1.7399B—no speed estimateToo large Qwen3.5 397B A17B403B—no speed estimateToo large Hermes 4 405B406B—no speed estimateToo large Hermes 3 405B Instruct406B—no speed estimateToo large GLM 5.1754B—no speed estimateToo large GLM 5.2753B—no speed estimateToo large MiniMax-01456B—no speed estimateToo large DeepSeek V3685B—no speed estimateToo large GLM 5754B—no speed estimateToo large DeepSeek V4.1 Flash763B—no speed estimateToo large MiMo-V2.5-Pro1T—no speed estimateToo large Kimi K2 09051T—no speed estimateToo large Kimi K2 07111T—no speed estimateToo large Ling-2.6-1T1T—no speed estimateToo large DeepSeek V3.1 Terminus685B—no speed estimateToo large DeepSeek V3.2685B—no speed estimateToo large DeepSeek V3.2 Exp685B—no speed estimateToo large Ring-2.6-1T1T—no speed estimateToo large Kimi K2.7 Code1.1T—no speed estimateToo large Kimi K2.61.1T—no speed estimateToo large Kimi K2.51.1T—no speed estimateToo large Hy4 preview780B—no speed estimateToo large Inkling952B—no speed estimateToo large Kimi K2 Thinking1.1T—no speed estimateToo large LongCat 2.01.8T—no speed estimateToo large Qwen3.8 2.4T A95B2.4T—no speed estimateToo large DeepSeek V4 Pro1.6T—no speed estimateToo large Kimi K32.8T—no speed estimateToo large

224 models have a verdict on this device: 154 fit in memory, 9 spill into system memory and 61 are too large. Every one of them is on this page.

03

Other Ampere cards

The same generation in other memory sizes. Memory is what decides which models fit.

GeForce RTX 3060 8GB8 GB · less memory GeForce RTX 3080 10GB10 GB · less memory GeForce RTX 3060 12GB12 GB · less memory GeForce RTX 3090 Ti24 GB · less memory GeForce RTX 309024 GB · less memory

Something wrong on this page? Tell us