models · deepseek-ai

DeepSeek-R1-Distill-Qwen-14B

Qwen-14B distilled from DeepSeek-R1 reasoning traces.

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.

Weight file SHA-256	2691341a5246570c477f1a21284447d0a4e9634ad5ef7a6660acbbc87105630e
Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	deepseek-ai
Origin	China
Licence	MIT
Parameters	14,770,033,664 (14.8B)
Architecture	qwen2
Layers	48
Hidden size	5120
Attention	GQA (40 heads, 8 KV)
Native precision	BF16
Pulls recorded here	64,018
Downloads reported upstream	340,597

Reported scores

MMLU-Pro	74
GPQA Diamond	48.4
AIME 2025	55.7
MATH-500	94.9
LiveCodeBench	37.6
IFBench	22.1
Humanity's Last Exam	4.1

Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.

Elsewhere in the registry

All models → Browse with filters → What will run on my hardware? →

Registry record as of 2026-06-11. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.