models · qwen

Qwen3 Coder Next

Qwen3 Coder Next — catalogued from third-party evaluation data; no weights held by Sovereign Frontier.

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	qwen
Origin	China
Licence	Apache-2.0
Parameters	79,674,391,296 (79.7B)
Context window	262,144 tokens
Modality	text->text
Architecture	qwen3_next
Layers	48
Hidden size	2048
Attention	GQA (16 heads, 2 KV)
Native precision	BF16
Pulls recorded here	9
Downloads reported upstream	385,440

Reported scores

GPQA Diamond	73.7
IFBench	35.2
Humanity's Last Exam	10.1

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
Intel Arc Pro B70 ×2 devices	llama.cpp	UD-Q4_K_XL	58.5 tok/s @ 2,048	candidate	localmaxxing
Apple M3 Ultra 512GB	llama.cpp	Q5_K_XL	57.1 tok/s @ 8,192	candidate	localmaxxing
Ryzen AI Max+ 395	llama.cpp	Q4_K_M	55.8 tok/s @ 16,384	candidate	localmaxxing
Ryzen AI Max+ 395	llama.cpp	Q5_K_M	51.4 tok/s @ 32,768	candidate	localmaxxing
Measured outside 2K–32K context — decode speed depends heavily on context, so these are not comparable with the rows above
Intel Arc Pro B70 ×4 devices	vllm	safetensors FP8	71.7 tok/s @ 262,144	candidate	localmaxxing
Radeon AI PRO R9700 ×3 devices	llama.cpp	UD-Q5_K_M	68.9 tok/s @ 785	candidate	localmaxxing
Ryzen AI Max+ 395	llama.cpp	UD-Q5_K_M	47.0 tok/s @ 676	candidate	localmaxxing

From local-ai-registry (MIT), commit 124959d: 10 runs across 6 machines, 0 validated — model revision and runtime pinned, launch accepted — and 10 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 2026-08-13. 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.