What can the 2× RTX PRO 6000 Blackwell run?
| Text models: 80 | Visual models: 0 | Strongest first |
- Memory
- 192 GB
- Bandwidth
- 1,792 GB/s each
- Maker
- NVIDIA
Open the calculator on this machineRTX PRO 6000 Blackwell in our inventory
Text models that run on it
| Model | Best fit | Context | Speed | Strongest at |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | 1.6-bit | 1M | 193 tok/s | Chat, Coding, Agents, Docs |
| GLM-5.3 | 1.6-bit | 352K | 89 tok/s | Chat, Coding, Agents, Docs |
| GLM-5.3 Flash | 3-bit | 1M | 102 tok/s | Chat, Coding, Agents, Docs |
| Qwen3.8 Flash-Next | 8-bit | 104K | 124 tok/s | Chat, Coding, Agents |
| Muse Spark Open 816B A42B | 1.6-bit | 352K | 94 tok/s | Chat, Docs |
| MiMo V2.6 Flash | FP4 + FP8 | 896K | 87 tok/s | Coding, Agents |
| MiniMax M3 | 2-bit | 256K | 95 tok/s | Docs |
| DeepSeek V4 Flash | FP4 + FP8 | 1M | 57 tok/s | Docs |
| Hy3 | 4-bit | 44K | 67 tok/s | Chat, Coding, Agents, Docs |
| Nemotron 3 Ultra 550B A55B | 1.6-bit | 256K | 63 tok/s | Chat, Coding, Docs |
| Qwen3.5 397B A17B | 2-bit | 256K | 113 tok/s | Agents, Docs |
| MiniMax M2.7 | 6-bit | 24K | 97 tok/s | Coding, Agents |
| DeepSeek V3.2 | 1.6-bit | 160K | 103 tok/s | Chat, Coding, Agents, Docs |
| Mistral Medium 3.5 128B | FP8 | 160K | 9.3 tok/s | Chat, Coding, Agents, Docs |
| Qwen3.5 122B A10B | 8-bit | 256K | 87 tok/s | Chat, Coding, Agents, Docs |
| Nemotron 3 Super 120B A12B | 8-bit | 256K | 64 tok/s | Chat, Coding, Agents, Docs |
| Nemotron 3.5 Bolt 74B A9B | 8-bit | 256K | 77 tok/s | Chat, Coding, Agents, Docs |
| Mistral Small 4 119B | FP8 | 256K | 135 tok/s | Chat, Docs |
| gpt-oss 120B | MXFP4 | 128K | 197 tok/s | Chat, Coding |
| Qwen3 Coder Next 80B | 8-bit | 256K | 182 tok/s | Coding, Agents |
| Llama 3.3 70B | 8-bit | 128K | 16 tok/s | Chat, Coding, Agents, Docs |
| Inkling | 1.6-bit | 4K | 94 tok/s | Text and images |
| DeepSeek R1 | 1.6-bit | 160K | 98 tok/s | Not rated |
| DeepSeek V3 | 1.6-bit | 160K | 98 tok/s | Not rated |
| GLM 5 | 1.6-bit | 198K | 86 tok/s | Not rated |
| GLM 4.5 Air | 8-bit | 128K | 65 tok/s | Not rated |
| Inkling Small | 5-bit | 4K | 111 tok/s | Text and images |
| MiniMax M2.5 | 6-bit | 24K | 89 tok/s | Not rated |
| GLM 5.1 | 1.6-bit | 198K | 86 tok/s | Not rated |
| Laguna M.1 | 6-bit | 28K | 51 tok/s | Not rated |
| Laguna S 2.1 | 8-bit | 1M | 100 tok/s | Not rated |
| Qwen3 VL 235B A22B Instruct | 5-bit | 128K | 55 tok/s | Text and images |
| GLM 5.2 | 1.6-bit | 352K | 87 tok/s | Not rated |
| Qwen3 235B A22B | 5-bit | 40K | 55 tok/s | Not rated |
| Ornith 1.5 122B | 8-bit | 256K | 72 tok/s | Not rated |
| Ornith 1.5 397B | 2-bit | 256K | 91 tok/s | Not rated |
| Ornith 1.0 397B | 2-bit | 256K | 110 tok/s | Not rated |
| Step 3.5 Flash | 6-bit | 72K | 113 tok/s | Not rated |
| DeepSeek V3 0324 | 1.6-bit | 160K | 97 tok/s | Not rated |
| Qwen2.5 72B Instruct | 8-bit | 32K | 16 tok/s | Not rated |
| Qwen3 Next 80B A3B Instruct | 8-bit | 256K | 182 tok/s | Not rated |
| DeepSeek R1 0528 | 1.6-bit | 160K | 97 tok/s | Not rated |
| GLM 4.5 | 3-bit | 48K | 52 tok/s | Not rated |
| Llama 4 Scout 17B 16E Instruct | 8-bit | 384K | 55 tok/s | Text and images |
| MiniMax M2 | 6-bit | 24K | 89 tok/s | Not rated |
| MiMo V2.5 | 4-bit | 240K | 88 tok/s | Not rated |
| Qwen2.5 VL 72B Instruct | 8-bit | 125K | 16 tok/s | Text and images |
| Solar Open 100B | 8-bit | 128K | 76 tok/s | Not rated |
| GLM 5.3 Flash BF16 | 3-bit | 1M | 100 tok/s | Text and images |
| Qwen3 VL 235B A22B Thinking | 5-bit | 128K | 55 tok/s | Text and images |
| Qwen3 235B A22B Instruct 2507 | 5-bit | 136K | 55 tok/s | Not rated |
| NVIDIA Nemotron 3.5 Super VL 120B A12B BF16 | 8-bit | 1M | 64 tok/s | Text and images |
| Hy3 Preview | 4-bit | 36K | 67 tok/s | Not rated |
| Qwen3 Coder 480B A35B Instruct | 2-bit | 52K | 71 tok/s | Coding |
| GLM 4.7 | 3-bit | 48K | 52 tok/s | Not rated |
| Kimi Linear 48B A3B Instruct | 8-bit | 4K | 238 tok/s | Not rated |
| Qwen3 Next 80B A3B Thinking | 8-bit | 256K | 182 tok/s | Not rated |
| GLM 5.3 BF16 | 1.6-bit | 352K | 87 tok/s | Not rated |
| GLM 4.6 | 3-bit | 48K | 53 tok/s | Not rated |
| DeepSeek R1 Distill Llama 70B | 8-bit | 128K | 16 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 80 are shown.
Only just too big
These need up to a quarter more memory than the 2× RTX PRO 6000 Blackwell has. Spilling into system RAM or a lower precision can get them running, slowly.
Questions
What is the best LLM for the 2× RTX PRO 6000 Blackwell?
Of the open models we track, the strongest that run well on the 2× RTX PRO 6000 Blackwell are DeepSeek V4.1 Flash, GLM-5.3, GLM-5.3 Flash. 80 text models fit it in all.
Calculated from published specs, not benchmarked. All machines