← Every GPUAMD · 48 GB VRAM · 864 GB/s

What can the Radeon Pro W7900 run?

With 48 GB, 9 of 12 popular open models fit. The best pick is Qwen3 32B at about 24 tok/s, about reading speed.

ollama run qwen3:32b

First time? Install Ollama, then paste that into a terminal. Is this your machine? Check it on the homepage.

48 GB VRAM

Every model the Radeon Pro W7900 can run

  • Qwen3 4BQuick everyday chat and summaries
    ~190 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~91 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~59 tok/s
    Runs greatgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~51 tok/s
    Runs greatqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~150 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~28 tok/s
    Usablegemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~150 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~24 tok/s
    Usableqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    ~11 tok/s
    Usablellama3.3:70b
  • gpt-oss 120BOpenAI's largest open model
    needs 67 GB
    Too biggpt-oss:120b
  • Qwen3 235B-A22BAlibaba's flagship open model, for multi-GPU rigs
    needs 144 GB
    Too bigqwen3:235b
  • DeepSeek R1 671BThe full DeepSeek R1, for the biggest rigs
    needs 406 GB
    Too bigdeepseek-r1:671b
Common questions

Can the Radeon Pro W7900 run it?

Can the Radeon Pro W7900 run Qwen3 32B?

Yes. Qwen3 32B needs about 22 GB and the Radeon Pro W7900 has 48 GB of VRAM. Expect about 24 tok/s, about reading speed.

Can the Radeon Pro W7900 run Llama 3.3 70B?

Yes. Llama 3.3 70B needs about 45 GB and the Radeon Pro W7900 has 48 GB of VRAM. Expect about 11 tok/s, about reading speed.

Can the Radeon Pro W7900 run gpt-oss 120B?

No. gpt-oss 120B needs about 67 GB and the Radeon Pro W7900 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 32B, at about 24 tok/s.

How we estimate

Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (864 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.

Want something bigger?

The Ryzen AI Max+ 395 mini PC, 128 GB runs gpt-oss 120B at about 31 tok/s, from $3,400 used.

See the builds

Compare

Similar cards

Every GPU we track

Head to head

The Radeon Pro W7900 against its rivals

Every comparison