Skip to content

What can the RTX PRO 6000 Blackwell run?

What fits on the RTX PRO 6000 Blackwell
Text models: 119Visual models: 1Strongest first
Memory
96 GB
Bandwidth
1,792 GB/s
Maker
NVIDIA

Open the calculator on this machineRTX PRO 6000 Blackwell in our inventoryEvery model for 96 GB of VRAM

Text models that run on it

Text models that run on the RTX PRO 6000 Blackwell, best first
ModelBest fitContextSpeedStrongest at
Qwen3.8 Flash-Next3-bit256K188 tok/sChat, Coding, Agents
MiniMax M31.6-bit64K135 tok/sDocs
Qwen3.8 27B8-bit256K41 tok/sChat, Coding, Agents, Docs
Qwen3.5 397B A17B1.6-bit256K153 tok/sAgents, Docs
MiniMax M2.72-bit40K149 tok/sCoding, Agents
Muse Glimmer 30B8-bit128K39 tok/sDocs
Mistral Medium 3.5 128B4-bit52K16 tok/sChat, Coding, Agents, Docs
Qwen3.5 122B A10B5-bit256K115 tok/sChat, Coding, Agents, Docs
Nemotron 3 Super 120B A12B5-bit256K82 tok/sChat, Coding, Agents, Docs
Nemotron 3.5 Bolt 74B A9B8-bit256K77 tok/sChat, Coding, Agents, Docs
Qwen3.6 35B A3B8-bit256K200 tok/sChat, Coding, Agents, Docs
Gemma 4 31B8-bit256K35 tok/sChat, Coding, Agents, Docs
Gemma 4 26B A4B8-bit256K199 tok/sChat, Coding, Agents, Docs
GLM-4.7 Flash8-bit198K187 tok/sChat, Coding, Agents
Mistral Small 4 119B5-bit256K171 tok/sChat, Docs
gpt-oss 120BMXFP4128K197 tok/sChat, Coding
Qwen3 Coder Next 80B8-bit256K182 tok/sCoding, Agents
Nemotron 3.5 Lightning 30B A3B8-bit256K175 tok/sAgents, Docs
Devstral Small 2 24BFP8384K47 tok/sCoding
LFM2.5 24B A2B8-bit128K244 tok/sAgents
Mistral Small 3.2 24B8-bit128K48 tok/sChat, Coding, Agents
Llama 3.3 70B8-bit64K16 tok/sChat, Coding, Agents, Docs
Olmo 3.1 32B8-bit64K35 tok/sChat, Coding, Agents, Docs
Qwen3 32B8-bit40K34 tok/sNot rated
Qwen3.6 27B8-bit256K41 tok/sText and images
Qwen3 Coder 30B A3B Instruct8-bit256K184 tok/sCoding
Qwen3.5 27B8-bit256K41 tok/sText and images
Qwen3.5 35B A3B8-bit256K200 tok/sText and images
NVIDIA Nemotron 3 Nano 30B A3B BF168-bit256K175 tok/sNot rated
GLM 4.5 Air6-bit32K80 tok/sNot rated
Inkling Small2-bit4K168 tok/sText and images
Qwen3 30B A3B8-bit40K184 tok/sNot rated
MiniMax M2.52-bit40K139 tok/sNot rated
Qwen3 30B A3B Instruct 25078-bit256K184 tok/sNot rated
Laguna XS.28-bit256K202 tok/sNot rated
OTel 2.0 LLM 31B IT8-bit256K35 tok/sNot rated
Laguna M.12-bit40K89 tok/sNot rated
Qwen2.5 32B Instruct8-bit32K34 tok/sNot rated
MiniCPM V 4.7 35B A3B8-bit256K200 tok/sText and images
Laguna XS 2.18-bit256K202 tok/sNot rated
Diffusiongemma 26B A4B IT8-bit256K193 tok/sText and images
Qwen2.5 VL 32B Instruct8-bit125K34 tok/sText and images
Qwen2.5 Coder 32B Instruct8-bit32K34 tok/sCoding
Laguna S 2.15-bit256K130 tok/sNot rated
Qwen3 VL 30B A3B Instruct8-bit256K184 tok/sText and images
DeepSeek R1 Distill Qwen 32B8-bit128K34 tok/sNot rated
Gemma 3 27B IT8-bit128K42 tok/sText and images
Qwen3 VL 235B A22B Instruct2-bit40K82 tok/sText and images
Qwen3 235B A22B2-bit40K82 tok/sNot rated
Ornith 1.5 35B A3B8-bit256K200 tok/sNot rated
Ornith 1.5 122B5-bit256K98 tok/sNot rated
Ornith 1.5 397B1.6-bit256K129 tok/sNot rated
Qwen3 VL 32B Instruct8-bit224K34 tok/sText and images
Step 3.5 Flash2-bit52K181 tok/sNot rated
Qwen2.5 72B Instruct8-bit32K16 tok/sNot rated
Qwen3 Next 80B A3B Instruct8-bit256K182 tok/sNot rated
Llama 4 Scout 17B 16E Instruct6-bit36K68 tok/sText and images
MiniMax M22-bit40K139 tok/sNot rated
Qwen2.5 VL 72B Instruct8-bit56K16 tok/sText and images
Qwen1.5 7B8-bit32K143 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 119 are shown.

Image and video models

Image and video models that run on the RTX PRO 6000 Blackwell
ModelBest fitPer outputStrongest at
FLUX.2 [dev]16-bit31 sImages

Only just too big

These need up to a quarter more memory than the 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 RTX PRO 6000 Blackwell?

Of the open models we track, the strongest that run well on the RTX PRO 6000 Blackwell are Qwen3.8 Flash-Next, MiniMax M3, Qwen3.8 27B. 119 text models fit it in all.

Calculated from published specs, not benchmarked. All machines