Skip to content

What can the 8× RTX PRO 6000 Blackwell run?

What fits on the 8× RTX PRO 6000 Blackwell
Text models: 53Visual models: 0Strongest first
Memory
768 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

Text models that run on the 8× RTX PRO 6000 Blackwell, best first
ModelBest fitContextSpeedStrongest at
Kimi K31.6-bit1M43 tok/sChat, Coding, Agents, Docs
MiMo V2.6 ProFP4 + FP81M33 tok/sChat, Coding, Agents, Docs
DeepSeek V4.1 FlashFP4 + FP81M63 tok/sChat, Coding, Agents, Docs
GLM-5.3FP8208K27 tok/sChat, Coding, Agents, Docs
GLM-5.3 FlashFP81M57 tok/sChat, Coding, Agents, Docs
Qwen3.8 2.4T A95B1.6-bit256K46 tok/sChat, Coding, Agents
Muse Spark Open 816B A42B6-bit1M32 tok/sChat, Docs
MiniMax M38-bit1M43 tok/sDocs
DeepSeek V4 Pro2-bit1M55 tok/sChat, Coding, Agents, Docs
Kimi K2.6INT4256K25 tok/sChat, Coding, Agents, Docs
Hy38-bit256K44 tok/sChat, Coding, Agents, Docs
Nemotron 3 Ultra 550B A55B8-bit256K19 tok/sChat, Coding, Docs
Qwen3.5 397B A17B8-bit256K55 tok/sAgents, Docs
MiniMax M2.7FP8200K85 tok/sCoding, Agents
DeepSeek V3.2FP8160K29 tok/sChat, Coding, Agents, Docs
Inkling6-bit4K33 tok/sText and images
DeepSeek R1FP8160K28 tok/sNot rated
DeepSeek V3FP8160K28 tok/sNot rated
GLM 56-bit198K31 tok/sNot rated
Inkling Small8-bit4K82 tok/sText and images
MiniMax M2.5FP8192K77 tok/sNot rated
GLM 5.16-bit198K31 tok/sNot rated
Laguna M.18-bit256K42 tok/sNot rated
Qwen3 VL 235B A22B Instruct8-bit256K41 tok/sText and images
GLM 5.26-bit1M31 tok/sNot rated
Qwen3 235B A22B8-bit40K41 tok/sNot rated
Kimi K2 Instruct5-bit128K37 tok/sNot rated
Ornith 1.5 397B8-bit256K41 tok/sNot rated
Ornith 1.0 397B8-bit256K53 tok/sNot rated
Step 3.5 Flash8-bit256K94 tok/sNot rated
DeepSeek V3 0324FP8160K28 tok/sNot rated
DeepSeek R1 0528FP8160K28 tok/sNot rated
GLM 4.58-bit128K28 tok/sNot rated
MiniMax M2FP8192K77 tok/sNot rated
MiMo V2.5FP81M59 tok/sNot rated
GLM 5.3 Flash BF168-bit1M55 tok/sText and images
Qwen3 VL 235B A22B Thinking8-bit256K41 tok/sText and images
Qwen3 235B A22B Instruct 25078-bit256K41 tok/sNot rated
Hy3 Preview8-bit256K44 tok/sNot rated
Qwen3 Coder 480B A35B Instruct8-bit256K30 tok/sCoding
GLM 4.78-bit198K28 tok/sNot rated
GLM 5.3 BF166-bit1M31 tok/sNot rated
GLM 4.68-bit198K29 tok/sNot rated
DeepSeek V2 Chat8-bit160K46 tok/sNot rated
MiMo V2 FlashFP8256K62 tok/sNot rated
Command A Plus 05 2026 Bf168-bit195K43 tok/sText and images
K EXAONE 2.0 750B A37B6-bit256K35 tok/sNot rated
MiniMax M2.1FP8192K77 tok/sNot rated
Beam 1.0 501B A23B8-bit1M44 tok/sNot rated
Hy4 Preview6-bit1M27 tok/sNot rated
Intern S18-bit64K34 tok/sText and images
Step 3.7 Flash8-bit256K93 tok/sText and images
K2 Horizon 375B A23B8-bit512K43 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%.

Questions

What is the best LLM for the 8× RTX PRO 6000 Blackwell?

Of the open models we track, the strongest that run well on the 8× RTX PRO 6000 Blackwell are Kimi K3, MiMo V2.6 Pro, DeepSeek V4.1 Flash. 53 text models fit it in all.

Calculated from published specs, not benchmarked. All machines