← Every GPUIntel · 12 GB VRAM · 456 GB/s

What can the Arc B580 run?

With 12 GB, 4 of 12 popular open models fit. The best pick is Qwen3 14B at about 27 tok/s, about reading speed.

ollama run qwen3:14b

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

12 GB VRAM

Every model the Arc B580 can run

  • Qwen3 4BQuick everyday chat and summaries
    ~100 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~48 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~31 tok/s
    Runs greatgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~27 tok/s
    Usableqwen3:14b
  • 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 Arc B580 run it?

Can the Arc B580 run Gemma 3 12B?

Yes. Gemma 3 12B needs about 10 GB and the Arc B580 has 12 GB of VRAM. Expect about 31 tok/s, faster than you can read.

Can the Arc B580 run Qwen3 14B?

Yes. Qwen3 14B needs about 11 GB and the Arc B580 has 12 GB of VRAM. Expect about 27 tok/s, about reading speed.

Can the Arc B580 run gpt-oss 20B?

No. gpt-oss 20B needs about 16 GB and the Arc B580 has at most 12 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 14B, at about 27 tok/s.

How we estimate

Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (456 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 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 Arc B580 against its rivals

Every comparison