DE
DeepSeek
Language model · China ·Jan 2025

DeepSeek-R1-Distill-Qwen-7B

Language Open (Restricted)
7B
Parameters
25
Benchmarks

About DeepSeek-R1-Distill-Qwen-7B

DeepSeek-R1-Distill-Qwen-7B is an AI model developed by DeepSeek, in the language category, released in 2025, made available as an open-weights model with 7B params.

On this page you'll find DeepSeek-R1-Distill-Qwen-7B's full specifications, including 25 benchmark results. Review provider pricing and benchmark scores below, or compare DeepSeek-R1-Distill-Qwen-7B head-to-head with other language models.

Links

Run DeepSeek-R1-Distill-Qwen-7B locally — what to buy

Share this build ↗

Sized to what DeepSeek-R1-Distill-Qwen-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 DeepSeek-R1-Distill-Qwen-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.

DeepSeek-R1-Distill-Qwen-7B benchmark scores
Benchmark Category Score Variant
HumanEval code 79.89% cited-granite-3-2
HumanEval+ code 78.43% cited-granite-3-2
LiveCodeBench v5 code 37.6% cited-mimo
LiveCodeBench v6 code 23.9% cited-mimo
AlpacaEval 2 general 15.35% cited-granite-3-2
ArenaHard general 10.36% cited-granite-3-2
IFEval general 60.5% cited-mimo
IFEval general 59.1% cited-granite-3-2
MMLU general 50.72% cited-granite-3-2
MMLU-Pro general 53.5% cited-mimo
SuperGPQA knowledge 28.9 cited-mimo
AIME 2024 math 83.3% cons@64-cited-exaone
AIME 2024 math 55.5% pass@1-cited-exaone
AIME 2024 math 55.5% cited-mimo
AIME 2025 math 56.7% cons@64-cited-exaone
AIME 2025 math 38.8% cited-mimo
AIME 2025 math 38.5% pass@1-cited-exaone
GSM8K math 78.47% cited-granite-3-2
MATH-500 math 92.8% pass@1-cited-exaone
MATH-500 math 92.8% cited-mimo
BIG-Bench Hard reasoning 65.04% cited-granite-3-2
DROP reasoning 77% cited-mimo
DROP reasoning 42.76% cited-granite-3-2
GPQA Diamond reasoning 49.1% cited-mimo
TruthfulQA safety 47.14% cited-granite-3-2

More models like DeepSeek-R1-Distill-Qwen-7B

Frequently asked questions

What is DeepSeek-R1-Distill-Qwen-7B?

DeepSeek-R1-Distill-Qwen-7B is an AI model developed by DeepSeek, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created DeepSeek-R1-Distill-Qwen-7B?

DeepSeek-R1-Distill-Qwen-7B was developed by DeepSeek and released in 2025.

Is DeepSeek-R1-Distill-Qwen-7B open source or proprietary?

DeepSeek-R1-Distill-Qwen-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 DeepSeek-R1-Distill-Qwen-7B cost?

Pricing for DeepSeek-R1-Distill-Qwen-7B depends on the provider. See the providers table on this page for the latest API rates.

How does DeepSeek-R1-Distill-Qwen-7B perform on benchmarks?

DeepSeek-R1-Distill-Qwen-7B is benchmarked across 25 evaluations on GenAIList, including HumanEval (79.89%). 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 DeepSeek-R1-Distill-Qwen-7B?