← Every GPUNVIDIA · 10 or 12 GB VRAM · 760 GB/s

What can the RTX 3080 run?

With 10 GB, 3 of 12 popular open models fit. The best pick is Gemma 3 12B at about 52 tok/s, faster than you can read.

ollama run gemma3:12b

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

10 GB VRAM

Every model the RTX 3080 10 GB can run

3 of 12 fit. Best pick: Gemma 3 12B.

  • Qwen3 4BQuick everyday chat and summaries
    ~170 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~80 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~52 tok/s
    Runs greatgemma3:12b
  • 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
12 GB VRAM

Every model the RTX 3080 12 GB can run

4 of 12 fit. Best pick: Qwen3 14B.

  • Qwen3 4BQuick everyday chat and summaries
    ~170 tok/s
    Runs greatqwen3:4b
  • Qwen3 8BA solid all-rounder for chat and writing
    ~80 tok/s
    Runs greatqwen3:8b
  • Gemma 3 12BReads images as well as text
    ~52 tok/s
    Runs greatgemma3:12b
  • Qwen3 14BNoticeably smarter at reasoning and code
    ~45 tok/s
    Runs greatqwen3:14b
  • 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 RTX 3080 run it?

Can the RTX 3080 run Gemma 3 12B?

Yes. Gemma 3 12B needs about 10 GB and the RTX 3080 has 10 GB of VRAM. Expect about 52 tok/s, faster than you can read.

Can the RTX 3080 run Qwen3 14B?

Yes, with 12 GB or more. Qwen3 14B needs about 11 GB and the RTX 3080 has 12 GB of VRAM. Expect about 45 tok/s, faster than you can read. The 10 GB version doesn't have room.

Can the RTX 3080 run gpt-oss 20B?

No. gpt-oss 20B needs about 16 GB and the RTX 3080 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 45 tok/s.

Measured, not estimated

Real runs on the RTX 3080

Loading measured runs…

How we estimate

Generating a token reads the model's active weights from memory once, so speed is roughly memory bandwidth (760 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 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 RTX 3080 against its rivals

Every comparison