← Every GPUAMD · 16 GB VRAM · 640 GB/s

What can the RX 9070 run?

With 16 GB, 5 of 12 popular open models fit. The best pick is gpt-oss 20B at about 110 tok/s, faster than you can read.

ollama run gpt-oss:20b

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

16 GB VRAM

Every model the RX 9070 can run

  • Qwen3 4BQuick everyday chat and summaries
    ~140 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~68 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~43 tok/s
    Runs greatgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~38 tok/s
    Runs greatqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    ~110 tok/s
    Runs greatgpt-oss:20b
  • Gemma 3 27BGoogle's best open model for its size
    needs 19 GB
    Too biggemma3:27b
  • Qwen3 30B-A3B30B smarts at small-model speed
    needs 21 GB
    Too bigqwen3:30b
  • Qwen3 32BStrong coding and long answers
    needs 22 GB
    Too bigqwen3:32b
  • 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
Common questions

Can the RX 9070 run it?

Can the RX 9070 run Qwen3 14B?

Yes. Qwen3 14B needs about 11 GB and the RX 9070 has 16 GB of VRAM. Expect about 38 tok/s, faster than you can read.

Can the RX 9070 run gpt-oss 20B?

Yes. gpt-oss 20B needs about 16 GB and the RX 9070 has 16 GB of VRAM. Expect about 110 tok/s, faster than you can read.

Can the RX 9070 run Gemma 3 27B?

No. Gemma 3 27B needs about 19 GB and the RX 9070 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 110 tok/s.

Measured, not estimated

Real runs on the RX 9070

Loading measured runs…

How we estimate

Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (640 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.

Want something bigger?

The Used workstation + 2× Tesla P100 runs Qwen3 32B at about 20 tok/s, from $750 used.

See the builds

Compare

Similar cards

Every GPU we track

Head to head

The RX 9070 against its rivals

Every comparison