Qwen
Qwen
Language model · China ·Sep 2024

Qwen2.5-3B

Language Open Weights
3.1B
Parameters
17
Benchmarks

About Qwen2.5-3B

Qwen2.5-3B is an AI model developed by Qwen, in the language category, released in 2024, made available as an open-weights model with 3.1B params.

On this page you'll find Qwen2.5-3B's full specifications, including 17 benchmark results. Review provider pricing and benchmark scores below, or compare Qwen2.5-3B head-to-head with other language models.

Links

Run Qwen2.5-3B locally — what to buy

Share this build ↗

Sized to what Qwen2.5-3B 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 Qwen2.5-3B 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.

Qwen2.5-3B benchmark scores
Benchmark Category Score Variant
AlpacaEval 2 general 17.4% instruct-cited-exaone35
ArenaHard general 32% cited-phi4-mini
ArenaHard general 26.4% instruct-cited-exaone35
IFEval general 60.8% instruct-cited-exaone35
LiveBench general 25.7 instruct-cited-exaone35
MMLU general 65% cited-phi4-mini
MMLU-Pro general 44.7% cited-phi4-mini
MMMLU general 55.9% cited-phi4-mini
ARC-Challenge knowledge 82.6 cited-phi4-mini
GSM8K math 80.6% cited-phi4-mini
MATH math 61.7% cited-phi4-mini
MGSM math 53.5 cited-phi4-mini
BIG-Bench Hard reasoning 56.2% cited-phi4-mini
HellaSwag reasoning 74.6 cited-phi4-mini
PIQA reasoning 72.6 cited-phi4-mini
Winogrande reasoning 63.3 cited-phi4-mini
TruthfulQA safety 64.3% cited-phi4-mini

More models like Qwen2.5-3B

Frequently asked questions

What is Qwen2.5-3B?

Qwen2.5-3B is an AI model developed by Qwen, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Qwen2.5-3B?

Qwen2.5-3B was developed by Qwen and released in 2024.

Is Qwen2.5-3B open source or proprietary?

Qwen2.5-3B 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 Qwen2.5-3B cost?

Pricing for Qwen2.5-3B depends on the provider. See the providers table on this page for the latest API rates.

How does Qwen2.5-3B perform on benchmarks?

Qwen2.5-3B is benchmarked across 17 evaluations on GenAIList, including AlpacaEval 2 (17.4%). 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 Qwen2.5-3B?