Skip to content

What can the A100 80 GB SXM run?

What fits on the A100 80 GB SXM
Text models: 110Visual models: 9Strongest first
Memory
80 GB
Bandwidth
2,039 GB/s
Maker
NVIDIA

Open the calculator on this machine

Text models that run on it

Text models that run on the A100 80 GB SXM, best first
ModelBest fitContextSpeedStrongest at
Qwen3.8 Flash-Next2-bit256K220 tok/sChat, Coding, Agents
Qwen3.8 27B8-bit256K46 tok/sChat, Coding, Agents, Docs
Muse Glimmer 30B8-bit128K44 tok/sDocs
Mistral Medium 3.5 128B3-bit48K22 tok/sChat, Coding, Agents, Docs
Qwen3.5 122B A10B4-bit176K138 tok/sChat, Coding, Agents, Docs
Nemotron 3 Super 120B A12B4-bit256K95 tok/sChat, Coding, Agents, Docs
Nemotron 3.5 Bolt 74B A9B8-bit112K83 tok/sChat, Coding, Agents, Docs
Qwen3.6 35B A3B8-bit256K214 tok/sChat, Coding, Agents, Docs
Gemma 4 31B8-bit256K40 tok/sChat, Coding, Agents, Docs
Gemma 4 26B A4B8-bit256K216 tok/sChat, Coding, Agents, Docs
GLM-4.7 Flash8-bit198K198 tok/sChat, Coding, Agents
Mistral Small 4 119B4-bit256K203 tok/sChat, Docs
gpt-oss 120BMXFP4128K212 tok/sChat, Coding
Qwen3 Coder Next 80B6-bit256K215 tok/sCoding, Agents
Nemotron 3.5 Lightning 30B A3B8-bit256K186 tok/sAgents, Docs
Devstral Small 2 24BFP8320K53 tok/sCoding
LFM2.5 24B A2B8-bit128K257 tok/sAgents
Mistral Small 3.2 24B8-bit128K54 tok/sChat, Coding, Agents
Llama 3.3 70B8-bit16K18 tok/sChat, Coding, Agents, Docs
Olmo 3.1 32B8-bit64K39 tok/sChat, Coding, Agents, Docs
Qwen3 14B8-bit40K86 tok/sNot rated
Qwen3 32B8-bit40K39 tok/sNot rated
Qwen3.6 27B8-bit256K46 tok/sText and images
Qwen2.5 Coder 14B Instruct8-bit32K84 tok/sCoding
Qwen3 Coder 30B A3B Instruct8-bit256K196 tok/sCoding
Qwen3.5 27B8-bit256K46 tok/sText and images
Qwen3.5 35B A3B8-bit256K214 tok/sText and images
NVIDIA Nemotron 3 Nano 30B A3B BF168-bit256K186 tok/sNot rated
GLM 4.5 Air4-bit64K110 tok/sNot rated
Qwen3 30B A3B8-bit40K196 tok/sNot rated
Qwen3 30B A3B Instruct 25078-bit256K196 tok/sNot rated
Laguna XS.28-bit256K215 tok/sNot rated
OTel 2.0 LLM 31B IT8-bit256K40 tok/sNot rated
Qwen2.5 32B Instruct8-bit32K39 tok/sNot rated
MiniCPM V 4.7 35B A3B8-bit256K214 tok/sText and images
Qwen2.5 14B Instruct8-bit32K84 tok/sNot rated
Laguna XS 2.18-bit256K215 tok/sNot rated
Diffusiongemma 26B A4B IT8-bit256K209 tok/sText and images
Qwen2.5 VL 32B Instruct8-bit125K38 tok/sText and images
Qwen2.5 Coder 32B Instruct8-bit32K39 tok/sCoding
Laguna S 2.14-bit184K155 tok/sNot rated
Qwen3 VL 30B A3B Instruct8-bit256K196 tok/sText and images
DeepSeek R1 Distill Qwen 32B8-bit128K39 tok/sNot rated
Gemma 3 27B IT8-bit128K47 tok/sText and images
Ornith 1.5 35B A3B8-bit256K214 tok/sNot rated
Ornith 1.5 122B4-bit176K119 tok/sNot rated
GPT Neox 20B8-bit2K61 tok/sNot rated
Qwen3 VL 32B Instruct8-bit168K38 tok/sText and images
DeepSeek R1 Distill Qwen 14B8-bit128K84 tok/sNot rated
Qwen2.5 14B Instruct 1M8-bit320K84 tok/sNot rated
Qwen2.5 72B Instruct6-bit32K23 tok/sNot rated
Qwen3 Next 80B A3B Instruct6-bit256K215 tok/sNot rated
Llama 4 Scout 17B 16E Instruct5-bit16K84 tok/sText and images
Qwen2.5 VL 72B Instruct6-bit60K23 tok/sText and images
Qwen1.5 7B8-bit32K160 tok/sNot rated
Solar Open 100B5-bit36K113 tok/sNot rated
Qwen3 30B A3B Thinking 25078-bit256K196 tok/sNot rated
NVIDIA Nemotron 3.5 Super VL 120B A12B BF164-bit576K95 tok/sText and images
Gnani Evon V3.3 30B A3B8-bit128K186 tok/sNot rated
EXAONE 3.5 32B Instruct8-bit32K39 tok/sNot rated

Best fit is the highest quality, up to 8-bit, that leaves the use case’s context. Ranked by our use-case scores, then by Hugging Face downloads. Speeds are rough, plus or minus 25%. The top 60 of 110 are shown.

Image and video models

Image and video models that run on the A100 80 GB SXM
ModelBest fitPer outputStrongest at
MiniMax H316-bit3.4 minVideo
LTX-2.516-bit38 sVideo
Qwen-Image16-bit1.8 minImages
FLUX.2 [dev]16-bit50 sImages
Wan2.2 I2V A14B16-bit17 minVideo
Wan2.1 I2V 14B16-bit17 minVideo
Wan 2.1 T2V-14B16-bit21 minVideo
Qwen Image 251216-bit1.8 minImages
Wan 2.2 A14B16-bit17 minVideo

Only just too big

Questions

What is the best LLM for the A100 80 GB SXM?

Of the open models we track, the strongest that run well on the A100 80 GB SXM are Qwen3.8 Flash-Next, Qwen3.8 27B, Muse Glimmer 30B. 110 text models fit it in all.

Calculated from published specs, not benchmarked. All machines