models · deepseek-ai

DeepSeek-R1-Distill-Llama-70B

Llama-3-70B distilled from DeepSeek-R1 reasoning traces. Strong math and code at 70B scale.

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	e15541ba94dd226540a47bdec8ba43766e1144cc7007289b42712774363ff053
Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	deepseek-ai
Origin	China
Licence	MIT
Parameters	70,553,706,496 (70.6B)
Context window	8,192 tokens
Modality	text->text
Architecture	llama
Layers	80
Hidden size	8192
Attention	GQA (64 heads, 8 KV)
Native precision	BF16
Pulls recorded here	84,017
Downloads reported upstream	78,355

Reported scores

MMLU-Pro	79.5
GPQA Diamond	40.2
AIME 2025	53.7
MATH-500	93.5
LiveCodeBench	26.6
IFBench	27.6
Humanity's Last Exam	5.1

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.