models · deepseek-ai

DeepSeek-Coder-V2-Lite-Instruct

DeepSeek Coder V2 Lite 16B instruct. Strong coding in 338 programming languages.

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	4d76824f96728b9e789df3d7fd5509f52d6cc800e1d3e5500dea30b8ac3a368b
Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	deepseek-ai
Origin	China
Licence	DeepSeek-TOS
Publisher’s own licence statement	other
Parameters	15,706,484,224 (15.7B)
Architecture	deepseek_v2
Layers	27
Hidden size	2048
Attention	MLA (16 heads, 16 KV)
Native precision	BF16
Pulls recorded here	36,006
Downloads reported upstream	801,915

Reported scores

MMLU-Pro	42.9
GPQA Diamond	31.9
LiveCodeBench	15.8
Humanity's Last Exam	5.4

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.