What can the A100 80 GB SXM run?
| Text models: 110 | Visual models: 9 | Strongest first |
- Memory
- 80 GB
- Bandwidth
- 2,039 GB/s
- Maker
- NVIDIA
Text models that run on it
| Model | Best fit | Context | Speed | Strongest at |
|---|---|---|---|---|
| Qwen3.8 Flash-Next | 2-bit | 256K | 220 tok/s | Chat, Coding, Agents |
| Qwen3.8 27B | 8-bit | 256K | 46 tok/s | Chat, Coding, Agents, Docs |
| Muse Glimmer 30B | 8-bit | 128K | 44 tok/s | Docs |
| Mistral Medium 3.5 128B | 3-bit | 48K | 22 tok/s | Chat, Coding, Agents, Docs |
| Qwen3.5 122B A10B | 4-bit | 176K | 138 tok/s | Chat, Coding, Agents, Docs |
| Nemotron 3 Super 120B A12B | 4-bit | 256K | 95 tok/s | Chat, Coding, Agents, Docs |
| Nemotron 3.5 Bolt 74B A9B | 8-bit | 112K | 83 tok/s | Chat, Coding, Agents, Docs |
| Qwen3.6 35B A3B | 8-bit | 256K | 214 tok/s | Chat, Coding, Agents, Docs |
| Gemma 4 31B | 8-bit | 256K | 40 tok/s | Chat, Coding, Agents, Docs |
| Gemma 4 26B A4B | 8-bit | 256K | 216 tok/s | Chat, Coding, Agents, Docs |
| GLM-4.7 Flash | 8-bit | 198K | 198 tok/s | Chat, Coding, Agents |
| Mistral Small 4 119B | 4-bit | 256K | 203 tok/s | Chat, Docs |
| gpt-oss 120B | MXFP4 | 128K | 212 tok/s | Chat, Coding |
| Qwen3 Coder Next 80B | 6-bit | 256K | 215 tok/s | Coding, Agents |
| Nemotron 3.5 Lightning 30B A3B | 8-bit | 256K | 186 tok/s | Agents, Docs |
| Devstral Small 2 24B | FP8 | 320K | 53 tok/s | Coding |
| LFM2.5 24B A2B | 8-bit | 128K | 257 tok/s | Agents |
| Mistral Small 3.2 24B | 8-bit | 128K | 54 tok/s | Chat, Coding, Agents |
| Llama 3.3 70B | 8-bit | 16K | 18 tok/s | Chat, Coding, Agents, Docs |
| Olmo 3.1 32B | 8-bit | 64K | 39 tok/s | Chat, Coding, Agents, Docs |
| Qwen3 14B | 8-bit | 40K | 86 tok/s | Not rated |
| Qwen3 32B | 8-bit | 40K | 39 tok/s | Not rated |
| Qwen3.6 27B | 8-bit | 256K | 46 tok/s | Text and images |
| Qwen2.5 Coder 14B Instruct | 8-bit | 32K | 84 tok/s | Coding |
| Qwen3 Coder 30B A3B Instruct | 8-bit | 256K | 196 tok/s | Coding |
| Qwen3.5 27B | 8-bit | 256K | 46 tok/s | Text and images |
| Qwen3.5 35B A3B | 8-bit | 256K | 214 tok/s | Text and images |
| NVIDIA Nemotron 3 Nano 30B A3B BF16 | 8-bit | 256K | 186 tok/s | Not rated |
| GLM 4.5 Air | 4-bit | 64K | 110 tok/s | Not rated |
| Qwen3 30B A3B | 8-bit | 40K | 196 tok/s | Not rated |
| Qwen3 30B A3B Instruct 2507 | 8-bit | 256K | 196 tok/s | Not rated |
| Laguna XS.2 | 8-bit | 256K | 215 tok/s | Not rated |
| OTel 2.0 LLM 31B IT | 8-bit | 256K | 40 tok/s | Not rated |
| Qwen2.5 32B Instruct | 8-bit | 32K | 39 tok/s | Not rated |
| MiniCPM V 4.7 35B A3B | 8-bit | 256K | 214 tok/s | Text and images |
| Qwen2.5 14B Instruct | 8-bit | 32K | 84 tok/s | Not rated |
| Laguna XS 2.1 | 8-bit | 256K | 215 tok/s | Not rated |
| Diffusiongemma 26B A4B IT | 8-bit | 256K | 209 tok/s | Text and images |
| Qwen2.5 VL 32B Instruct | 8-bit | 125K | 38 tok/s | Text and images |
| Qwen2.5 Coder 32B Instruct | 8-bit | 32K | 39 tok/s | Coding |
| Laguna S 2.1 | 4-bit | 184K | 155 tok/s | Not rated |
| Qwen3 VL 30B A3B Instruct | 8-bit | 256K | 196 tok/s | Text and images |
| DeepSeek R1 Distill Qwen 32B | 8-bit | 128K | 39 tok/s | Not rated |
| Gemma 3 27B IT | 8-bit | 128K | 47 tok/s | Text and images |
| Ornith 1.5 35B A3B | 8-bit | 256K | 214 tok/s | Not rated |
| Ornith 1.5 122B | 4-bit | 176K | 119 tok/s | Not rated |
| GPT Neox 20B | 8-bit | 2K | 61 tok/s | Not rated |
| Qwen3 VL 32B Instruct | 8-bit | 168K | 38 tok/s | Text and images |
| DeepSeek R1 Distill Qwen 14B | 8-bit | 128K | 84 tok/s | Not rated |
| Qwen2.5 14B Instruct 1M | 8-bit | 320K | 84 tok/s | Not rated |
| Qwen2.5 72B Instruct | 6-bit | 32K | 23 tok/s | Not rated |
| Qwen3 Next 80B A3B Instruct | 6-bit | 256K | 215 tok/s | Not rated |
| Llama 4 Scout 17B 16E Instruct | 5-bit | 16K | 84 tok/s | Text and images |
| Qwen2.5 VL 72B Instruct | 6-bit | 60K | 23 tok/s | Text and images |
| Qwen1.5 7B | 8-bit | 32K | 160 tok/s | Not rated |
| Solar Open 100B | 5-bit | 36K | 113 tok/s | Not rated |
| Qwen3 30B A3B Thinking 2507 | 8-bit | 256K | 196 tok/s | Not rated |
| NVIDIA Nemotron 3.5 Super VL 120B A12B BF16 | 4-bit | 576K | 95 tok/s | Text and images |
| Gnani Evon V3.3 30B A3B | 8-bit | 128K | 186 tok/s | Not rated |
| EXAONE 3.5 32B Instruct | 8-bit | 32K | 39 tok/s | Not 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
| Model | Best fit | Per output | Strongest at |
|---|---|---|---|
| MiniMax H3 | 16-bit | 3.4 min | Video |
| LTX-2.5 | 16-bit | 38 s | Video |
| Qwen-Image | 16-bit | 1.8 min | Images |
| FLUX.2 [dev] | 16-bit | 50 s | Images |
| Wan2.2 I2V A14B | 16-bit | 17 min | Video |
| Wan2.1 I2V 14B | 16-bit | 17 min | Video |
| Wan 2.1 T2V-14B | 16-bit | 21 min | Video |
| Qwen Image 2512 | 16-bit | 1.8 min | Images |
| Wan 2.2 A14B | 16-bit | 17 min | Video |
Only just too big
- MiniMax M3
- Qwen3.5 397B A17B
- MiniMax M2.7
- Inkling Small
- MiniMax M2.5
- Laguna M.1
- Qwen3 VL 235B A22B Instruct
- Qwen3 235B A22B
- Ornith 1.5 397B
- Step 3.5 Flash
- MiniMax M2
- Qwen3 VL 235B A22B Thinking
- Qwen3 235B A22B Instruct 2507
- Qwen3 Coder 480B A35B Instruct
- DeepSeek V2 Chat
- Command A Plus 05 2026 Bf16
- MiniMax M2.1
- Beam 1.0 501B A23B
- Intern S1
- Step 3.7 Flash
These need up to a quarter more memory than the A100 80 GB SXM has. Spilling into system RAM or a lower precision can get them running, slowly.
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