← Every GPUAMD · 8 GB VRAM · 224 GB/s

What can the RX 6600 run?

With 8 GB, 2 of 12 popular open models fit. The best pick is Qwen3 8B at about 24 tok/s, about reading speed.

ollama run qwen3:8b

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

8 GB VRAM

Every model the RX 6600 can run

  • Qwen3 4BQuick everyday chat and summaries
    ~49 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~24 tok/s
    Usableqwen3:8b
  • Gemma 3 12BReads images as well as text
    needs 10 GB
    Too biggemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    needs 11 GB
    Too bigqwen3:14b
  • gpt-oss 20BOpenAI's open model. Fast, strong reasoning
    needs 16 GB
    Too biggpt-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 6600 run it?

Can the RX 6600 run Qwen3 4B?

Yes. Qwen3 4B needs about 4 GB and the RX 6600 has 8 GB of VRAM. Expect about 49 tok/s, faster than you can read.

Can the RX 6600 run Qwen3 8B?

Yes. Qwen3 8B needs about 7 GB and the RX 6600 has 8 GB of VRAM. Expect about 24 tok/s, about reading speed.

Can the RX 6600 run Gemma 3 12B?

No. Gemma 3 12B needs about 10 GB and the RX 6600 has at most 8 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 8B, 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 (224 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 Used desktop + RTX 3060 12 GB runs Qwen3 14B at about 21 tok/s, from $600 used.

See the builds

Compare

Similar cards

Every GPU we track

Head to head

The RX 6600 against its rivals

Every comparison