Qwen
Qwen
Language model · China ·Apr 2025

Qwen3-0.6B

Language Open (Restricted)
600M
Parameters
52
Benchmarks

About Qwen3-0.6B

Qwen3-0.6B is an AI model developed by Qwen, in the language category, released in 2025, made available as an open-weights model with 0.6B params.

On this page you'll find Qwen3-0.6B's full specifications, including 52 benchmark results. Review provider pricing and benchmark scores below, or compare Qwen3-0.6B head-to-head with other language models.

Links

Run Qwen3-0.6B locally — what to buy

Share this build ↗

Sized to what Qwen3-0.6B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Software support

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Community

Would you run Qwen3-0.6B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Qwen3-0.6B benchmark scores
Benchmark Category Score Variant
LiveCodeBench v5 code 12.3% thinking-pass@1
LiveCodeBench v5 code 3.6% non-thinking-pass@1
LiveCodeBench v5 code 3.6% non-reasoning
LiveCodeBench v6 code 6.9% non-reasoning
AlignBench v1.1 general 6.1 thinking-v1-1
AlignBench v1.1 general 5.6 non-thinking-v1-1
ArenaHard general 8.5% thinking
ArenaHard general 6.5% non-thinking
C-Eval general 50.4% thinking
C-Eval general 42.6% non-thinking
Creative Writing v3 general 30.6 thinking
Creative Writing v3 general 28.4 non-thinking
IFEval general 59.2% thinking-strict-prompt
IFEval general 54.5% non-reasoning
IFEval general 54.5% non-thinking-strict-prompt
LiveBench general 30.3 thinking-2024-11-25
LiveBench general 21.8 non-thinking-2024-11-25
MMLU-Pro general 26.6% non-reasoning
MMLU-Redux general 55.6% thinking
MMLU-Redux general 44.6% non-thinking
MMLU-Redux general 44.6% non-reasoning
MMMLU general 43.1% thinking-14lang
MMMLU general 37.1% non-thinking-14lang
Multi-IF general 36.1 thinking
Multi-IF general 33.3 non-thinking
WritingBench general 5.61 thinking
WritingBench general 5.13 non-thinking
INCLUDE knowledge 35.9 thinking
INCLUDE knowledge 34.4 non-thinking
AIME 2024 math 10.7% thinking
AIME 2024 math 3.4% non-thinking
AIME 2025 math 15.1% thinking
AIME 2025 math 2.6% non-reasoning
AIME 2025 math 2.6% non-thinking
MATH-500 math 77.6% thinking
MATH-500 math 55.2% non-thinking
MT-AIME 2024 math 7.8 thinking-mt-2024
MT-AIME 2024 math 1.5 non-thinking-mt-2024
PolyMath-en math 11.4 thinking
PolyMath-en math 4.6 non-thinking
AutoLogi reasoning 61.6 thinking
AutoLogi reasoning 37.4 non-thinking
GPQA Diamond reasoning 27.9% thinking
GPQA Diamond reasoning 22.9% non-thinking
GPQA Diamond reasoning 22.9% non-reasoning
MLogiQA reasoning 40.9 thinking
MLogiQA reasoning 37.3 non-thinking
ZebraLogic reasoning 30.3% thinking
ZebraLogic reasoning 4.2% non-thinking
BFCL v3 tool-use 46.4% thinking
BFCL v3 tool-use 44.1% non-thinking
BFCL v3 tool-use 44.1% non-reasoning

More models like Qwen3-0.6B

Frequently asked questions

What is Qwen3-0.6B?

Qwen3-0.6B is an AI model developed by Qwen, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Qwen3-0.6B?

Qwen3-0.6B was developed by Qwen and released in 2025.

Is Qwen3-0.6B open source or proprietary?

Qwen3-0.6B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Qwen3-0.6B cost?

Pricing for Qwen3-0.6B depends on the provider. See the providers table on this page for the latest API rates.

How does Qwen3-0.6B perform on benchmarks?

Qwen3-0.6B is benchmarked across 52 evaluations on GenAIList, including LiveCodeBench v5 (12.3%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about Qwen3-0.6B?