What can the Quadro RTX 8000 run?
With 48 GB, 9 of 12 popular open models fit. The best pick is Qwen3 30B-A3B at about 120 tok/s, faster than you can read.
ollama run qwen3:30bFirst time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.
Every model the Quadro RTX 8000 can run
- Qwen3 4BQuick everyday chat and summaries~150 tok/sRuns great
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~71 tok/sRuns great
qwen3:8b - Gemma 3 12BReads images as well as text~46 tok/sRuns great
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and code~40 tok/sRuns great
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoning~120 tok/sRuns great
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its size~22 tok/sUsable
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speed~120 tok/sRuns great
qwen3:30b - Qwen3 32BStrong coding and long answers~18 tok/sUsable
qwen3:32b - Llama 3.3 70BClose to the big cloud models~9 tok/sSlow
llama3.3:70b - gpt-oss 120BOpenAI's largest open modelneeds 67 GBToo big
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 Quadro RTX 8000 run it?
Can the Quadro RTX 8000 run Qwen3 32B?
Yes. Qwen3 32B needs about 22 GB and the Quadro RTX 8000 has 48 GB of VRAM. Expect about 18 tok/s, about reading speed.
Can the Quadro RTX 8000 run Llama 3.3 70B?
Yes. Llama 3.3 70B needs about 45 GB and the Quadro RTX 8000 has 48 GB of VRAM. Expect about 9 tok/s, slow, but it works.
Can the Quadro RTX 8000 run gpt-oss 120B?
No. gpt-oss 120B needs about 67 GB and the Quadro RTX 8000 has at most 48 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 Qwen3 30B-A3B, at about 120 tok/s.
Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (672 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 one yourself? Send us the number.
The Ryzen AI Max+ 395 mini PC, 128 GB runs gpt-oss 120B at about 31 tok/s, from $3,400 used.