What can the RTX Pro 6000 Blackwell run?
With 96 GB, 10 of 12 popular open models fit. The best pick is gpt-oss 120B at about 220 tok/s, faster than you can read.
ollama run gpt-oss:120bFirst time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.
Every model the RTX Pro 6000 Blackwell can run
- Qwen3 4BQuick everyday chat and summaries~390 tok/sRuns great
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~190 tok/sRuns great
qwen3:8b - Gemma 3 12BReads images as well as text~120 tok/sRuns great
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and code~110 tok/sRuns great
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoning~310 tok/sRuns great
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its size~58 tok/sRuns great
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speed~310 tok/sRuns great
qwen3:30b - Qwen3 32BStrong coding and long answers~49 tok/sRuns great
qwen3:32b - Llama 3.3 70BClose to the big cloud models~23 tok/sUsable
llama3.3:70b - gpt-oss 120BOpenAI's largest open model~220 tok/sRuns great
gpt-oss:120b - Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigsneeds 144 GBToo big
qwen3:235b - DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigsneeds 406 GBToo big
deepseek-r1:671b
Can the RTX Pro 6000 Blackwell run it?
Can the RTX Pro 6000 Blackwell run Llama 3.3 70B?
Yes. Llama 3.3 70B needs about 45 GB and the RTX Pro 6000 Blackwell has 96 GB of VRAM. Expect about 23 tok/s, about reading speed.
Can the RTX Pro 6000 Blackwell run gpt-oss 120B?
Yes. gpt-oss 120B needs about 67 GB and the RTX Pro 6000 Blackwell has 96 GB of VRAM. Expect about 220 tok/s, faster than you can read.
Can the RTX Pro 6000 Blackwell run Qwen3 235B-A22B?
No. Qwen3 235B-A22B needs about 144 GB and the RTX Pro 6000 Blackwell has at most 96 GB of VRAM. Ollama can still start it by putting part of the model in system RAM, but it runs several times slower. The most capable model it runs well is gpt-oss 120B, at about 220 tok/s.
Real runs on the RTX Pro 6000 Blackwell
Loading measured runs…
Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (1792 GB/s) divided by the active weight size, with efficiency calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. Real results are usually within about a third. Measured runs are on the leaderboard.
The Dell DSS 8440 + 10× Tesla P100 runs Qwen3 235B-A22B at about 19 tok/s, from $5,100 used.