What can the RX 6950 XT run?
With 16 GB, 5 of 12 popular open models fit. The best pick is gpt-oss 20B at about 100 tok/s, faster than you can read.
ollama run gpt-oss:20bFirst time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.
Every model the RX 6950 XT can run
- Qwen3 4BQuick everyday chat and summaries~130 tok/sRuns great
qwen3:4b - Qwen3 8BA solid all-rounder for chat and writing~61 tok/sRuns great
qwen3:8b - Gemma 3 12BReads images as well as text~39 tok/sRuns great
gemma3:12b - Qwen3 14BNoticeably smarter at reasoning and code~34 tok/sRuns great
qwen3:14b - gpt-oss 20BOpenAI's open model. Fast, strong reasoning~100 tok/sRuns great
gpt-oss:20b - Gemma 3 27BGoogle's best open model for its sizeneeds 19 GBToo big
gemma3:27b - Qwen3 30B-A3B30B smarts at small-model speedneeds 21 GBToo big
qwen3:30b - Qwen3 32BStrong coding and long answersneeds 22 GBToo big
qwen3:32b - Llama 3.3 70BClose to the big cloud modelsneeds 45 GBToo big
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 RX 6950 XT run it?
Can the RX 6950 XT run Qwen3 14B?
Yes. Qwen3 14B needs about 11 GB and the RX 6950 XT has 16 GB of VRAM. Expect about 34 tok/s, faster than you can read.
Can the RX 6950 XT run gpt-oss 20B?
Yes. gpt-oss 20B needs about 16 GB and the RX 6950 XT has 16 GB of VRAM. Expect about 100 tok/s, faster than you can read.
Can the RX 6950 XT run Gemma 3 27B?
No. Gemma 3 27B needs about 19 GB and the RX 6950 XT has at most 16 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 20B, at about 100 tok/s.
Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (576 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 Used workstation + 2× Tesla P100 runs Qwen3 32B at about 20 tok/s, from $750 used.