models · deepseek-ai

DeepSeek-Coder-V2-Instruct

DeepSeek Coder V2 MoE instruct model. 236B total / 21B active. State-of-the-art open-weight coding model with strong multi-language support.

Compare Verify

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	c0057d0523519c96108021eb4c2afaf5709e6a59e42eab930d6028422d5d84d6
Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	deepseek-ai
Origin	Recorded as a covered nation under 10 U.S.C. § 4872(f) — the PRC, Russia, Iran or North Korea. The registry did not record which.
Licence	DeepSeek
Publisher’s own licence statement	other
Parameters	235,741,434,880 (235.7B)
Context window	128K
Architecture	deepseek_v2
Layers	60
Hidden size	5120
Attention	MLA (128 heads, 128 KV)
Native precision	BF16
Pulls recorded here	480,019
Downloads reported upstream	10,376

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.