Qwen
Qwen
Language model · China ·Apr 2025

Qwen3-1.7B

Language Open (Restricted)
1.7B
Parameters
52
Benchmarks

About Qwen3-1.7B

Qwen3-1.7B is an AI model developed by Qwen, in the language category, released in 2025, made available as an open-weights model with 1.7B params.

On this page you'll find Qwen3-1.7B's full specifications, including 52 benchmark results. Review provider pricing and benchmark scores below, or compare Qwen3-1.7B head-to-head with other language models.

Links

Run Qwen3-1.7B locally — what to buy

Share this build ↗

Sized to what Qwen3-1.7B 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 Qwen3-1.7B 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.

Qwen3-1.7B benchmark scores
Benchmark Category Score Variant
LiveCodeBench v5 code 33.2% thinking-pass@1
LiveCodeBench v5 code 11.6% non-thinking-pass@1
LiveCodeBench v5 code 11.6% non-reasoning
LiveCodeBench v6 code 16.6% non-reasoning
AlignBench v1.1 general 7.6 thinking-v1-1
AlignBench v1.1 general 7.2 non-thinking-v1-1
ArenaHard general 43.1% thinking
ArenaHard general 36.9% non-thinking
C-Eval general 68.1% thinking
C-Eval general 61% non-thinking
Creative Writing v3 general 48 thinking
Creative Writing v3 general 43.6 non-thinking
IFEval general 72.5% thinking-strict-prompt
IFEval general 68.2% non-reasoning
IFEval general 68.2% non-thinking-strict-prompt
LiveBench general 51.1 thinking-2024-11-25
LiveBench general 35.6 non-thinking-2024-11-25
MMLU-Pro general 43.7% non-reasoning
MMLU-Redux general 73.9% thinking
MMLU-Redux general 64.4% non-thinking
MMLU-Redux general 63.4% non-reasoning
MMMLU general 59.1% thinking-14lang
MMMLU general 48.3% non-thinking-14lang
Multi-IF general 51.2 thinking
Multi-IF general 44.7 non-thinking
WritingBench general 7.02 thinking
WritingBench general 6.54 non-thinking
INCLUDE knowledge 51.8 thinking
INCLUDE knowledge 42.6 non-thinking
AIME 2024 math 48.3% thinking
AIME 2024 math 13.4% non-thinking
AIME 2025 math 36.8% thinking
AIME 2025 math 9.8% non-reasoning
AIME 2025 math 9.8% non-thinking
MATH-500 math 93.4% thinking
MATH-500 math 73% non-thinking
MT-AIME 2024 math 36.1 thinking-mt-2024
MT-AIME 2024 math 4.9 non-thinking-mt-2024
PolyMath-en math 25.2 thinking
PolyMath-en math 10.3 non-thinking
AutoLogi reasoning 83.2 thinking
AutoLogi reasoning 59.8 non-thinking
GPQA Diamond reasoning 40.1% thinking
GPQA Diamond reasoning 28.6% non-thinking
GPQA Diamond reasoning 28.6% non-reasoning
MLogiQA reasoning 56 thinking
MLogiQA reasoning 41.1 non-thinking
ZebraLogic reasoning 63.2% thinking
ZebraLogic reasoning 12.8% non-thinking
BFCL v3 tool-use 56.6% thinking
BFCL v3 tool-use 52.2% non-thinking
BFCL v3 tool-use 52.2% non-reasoning

More models like Qwen3-1.7B

Frequently asked questions

What is Qwen3-1.7B?

Qwen3-1.7B 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 Qwen3-1.7B?

Qwen3-1.7B was developed by Qwen and released in 2025.

Is Qwen3-1.7B open source or proprietary?

Qwen3-1.7B 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 Qwen3-1.7B cost?

Pricing for Qwen3-1.7B depends on the provider. See the providers table on this page for the latest API rates.

How does Qwen3-1.7B perform on benchmarks?

Qwen3-1.7B is benchmarked across 52 evaluations on GenAIList, including LiveCodeBench v5 (33.2%). 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 Qwen3-1.7B?