- Parameters
- 80B / 3B active
- Quant
- IQ4_XS
- Size
- 40.0 GB
- Family
- qwen3-next
qwen3-next-80b
RemovedMoEdeletedllama.cppmlx
Model card ↗Outcome as of 20 September 2026, from the seat registry. The write-up below was made when the model was tested.
Why it was tested
The incumbent. Chosen because 3B active parameters give MoE speed at 80B quality, and it fits at 40GB with room for a long context.
What came of it
GGUF deleted 2026-09-09 (40 GB); superseded by qwen3-next-80b-reap-mlx-mixed36 at 28 GB, which scores better on every suite. Router preset commented, not removed.
| Suite | Score | 95% interval | Passed | Runtime · profile | Recorded |
|---|---|---|---|---|---|
| grounding | 88.8% | 82.1–93.2 | Passed 111/125 | llama.cppextraction | 2026-09-05 |
| nullschema | 97.2% | 90.4–99.2 | Passed 70/72 | llama.cppextraction | 2026-09-05 |
| screening | 91.7% | 81.9–96.4 | Passed 55/60 | llama.cppextraction | 2026-09-05 |
Runs marked unenforced were measured through mlx_lm on a suite that requires constrained decoding. mlx_lm accepts the schema and ignores it, so those numbers do not measure what the suite is designed to measure. They are kept and labelled rather than deleted.
Every run log entry for this model (6)
| Finished | Suite | Runtime · profile | Score | Coverage | Grader · dataset · config |
|---|---|---|---|---|---|
| nullschemanullschema/1 | llama.cppextraction | 97.2% | Coverage 72/72 | g d7448e0f5fc3f9afd 3b91280bb40372efc 5913b00d3e8c6b3d | |
| screeningscreening/1 | llama.cppextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc ede1a2072fbaea6c | |
| groundinggrounding/1 | llama.cppextraction | 88.8% | Coverage 125/125 | g 30b933dcc6a7e2d4d dcb396faf8b83b0ac f34a40087b318cc6 | |
| nullschemanullschema/1 | llama.cppextraction | 97.2% | Coverage 72/72 | g d7448e0f5fc3f9afd 3b91280bb40372efc 5913b00d3e8c6b3d | |
| screeningscreening/1 | llama.cppextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc ede1a2072fbaea6c | |
| groundinggrounding/1 | llama.cppextraction | 88.8% | Coverage 125/125 | g 30b933dcc6a7e2d4d dcb396faf8b83b0ac f34a40087b318cc6 |
- Qwen3-Next-80B-A3B Instruct, REAP prunedMeasured, not seated
60B · MoE · IQ4_XS · 30.4 GB
Tested to find out whether expert pruning costs the extraction seat its abstention. The full model holds that seat at 40 GB, which is most of the memory budget on a 64 GB machine.
- Qwen3-Next-80B-A3B ThinkingRejected
80B · MoE · IQ4_XS · 40.0 GB
Tested to see whether reasoning improves extraction, on the assumption that thinking helps.