models · deepseek-ai

DeepSeek-V4.1-Flash

image-text-to-text model harvested from Hugging Face (trending). Catalogued at Quarantine — unverified, pending attestation.

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.

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	mit
Parameters	484,619,644,114 (484.6B)
Context window	1,048,576 tokens
Modality	text+image->text
Native precision	I8

Reported scores

Humanity's Last Exam	39.2

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

Measured on real hardware

None of these runs are ours. Each figure is the reporter’s, linked to their own evidence, under their own trust label. The number shown is single-stream decode — one user, concurrency 1 — because aggregate throughput across many users is a different quantity and reads as far faster than anyone will see.

Reported to local-ai-registry

Hardware	Engine	Build measured	Decode, 1 stream	Label	Reported by
RTX PRO 6000 Blackwell ×4 devices	vllm	—	281 tok/s @ 32,768	candidate	discord
RTX PRO 6000 Blackwell ×4 devices	vllm	—	261 tok/s @ 32,768	candidate	discord
Measured outside 2K–32K context — decode speed depends heavily on context, so these are not comparable with the rows above
RTX PRO 6000 Blackwell ×4 devices	vllm	safetensors FP8	123 tok/s	validated	0xsero
RTX PRO 6000 Blackwell ×4 devices	sglang	safetensors FP8	116 tok/s	candidate	0xsero
NVIDIA DGX Spark GB10 ×4 devices	sglang	safetensors FP8	49.3 tok/s	validated	0xsero
NVIDIA DGX Spark GB10 ×4 devices	sglang	safetensors FP8	39.4 tok/s	validated	0xsero

From local-ai-registry (MIT), commit 124959d: 14 runs across 2 machines, 3 validated — model revision and runtime pinned, launch accepted — and 11 candidate, their label for useful evidence without a reproducible-launch promise.

Elsewhere in the registry

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

Registry record as of 2026-09-10. 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.