← Every GPUAMD · 64 or 32 GB unified memory · 256 GB/s

What can the Ryzen AI Max 390 (Radeon 8050S) run?

With 64 GB, 9 of 12 popular open models fit. The best pick is Qwen3 30B-A3B at about 45 tok/s, faster than you can read.

ollama run qwen3:30b

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

32 GB unified memory · about 24 GB for models

Every model the Ryzen AI Max 390 (Radeon 8050S) 32 GB can run

8 of 12 fit. Best pick: Qwen3 30B-A3B.

  • Qwen3 4BQuick everyday chat and summaries
    ~56 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~27 tok/s
    Usableqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~17 tok/s
    Usablegemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~15 tok/s
    Usableqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~45 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~8 tok/s
    Slowgemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~45 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~7 tok/s
    Slowqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    needs 45 GB
    Too bigllama3.3:70b
  • 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
64 GB unified memory · about 48 GB for models

Every model the Ryzen AI Max 390 (Radeon 8050S) 64 GB can run

9 of 12 fit. Best pick: Qwen3 30B-A3B.

  • Qwen3 4BQuick everyday chat and summaries
    ~56 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~27 tok/s
    Usableqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~17 tok/s
    Usablegemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~15 tok/s
    Usableqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~45 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    ~8 tok/s
    Slowgemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    ~45 tok/s
    Runs greatqwen3:30b
  • Qwen3 32BStrong coding and long answers
    ~7 tok/s
    Slowqwen3:32b
  • Llama 3.3 70BClose to the big cloud models
    ~3 tok/s
    Slowllama3.3:70b
  • 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 Ryzen AI Max 390 (Radeon 8050S) run it?

Can the Ryzen AI Max 390 (Radeon 8050S) run Qwen3 32B?

Yes. Qwen3 32B needs about 22 GB and the Ryzen AI Max 390 (Radeon 8050S) with 32 GB of unified memory leaves about 24 GB for models. Expect about 7 tok/s, slow, but it works.

Can the Ryzen AI Max 390 (Radeon 8050S) run Llama 3.3 70B?

Yes, with 64 GB or more. Llama 3.3 70B needs about 45 GB and the Ryzen AI Max 390 (Radeon 8050S) with 64 GB of unified memory leaves about 48 GB for models. Expect about 3 tok/s, slow, but it works. The 32 GB version doesn't have room.

Can the Ryzen AI Max 390 (Radeon 8050S) run gpt-oss 120B?

No. gpt-oss 120B needs about 67 GB and the Ryzen AI Max 390 (Radeon 8050S) has at most 64 GB of unified memory, of which about 48 GB is usable for models. The most capable model it runs well is Qwen3 30B-A3B, at about 45 tok/s.

How we estimate

Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (256 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. The GPU shares memory with the system, so we count about three quarters of it for models. 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 Ryzen AI Max 390 (Radeon 8050S) against its rivals

Every comparison