- Parameters
- 122B / 10B active
- Quant
- IQ3
- Size
- 45.0 GB
- Family
- qwen3.x
qwen3.5-122b-a10b-iq3
RemovedMoEdeletedllama.cpp
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
Tested as the largest MoE that would fit, on the assumption that more parameters would win.
What came of it
Deleted during a disk sweep. Later benchmarks put a 27B dense model ahead of it on general intelligence indices, which supports the decision after the fact rather than before it.
| Suite | Score | 95% interval | Passed | Runtime · profile | Recorded |
|---|---|---|---|---|---|
| grounding | 80.8% | 73.0–86.7 | Passed 101/125 | llama.cppextraction | 2026-08-26 |
| nullschema | 45.8% | 34.8–57.3 | Passed 33/72 | llama.cppextraction | 2026-08-26 |
| screening | 88.3% | 77.8–94.2 | Passed 53/60 | llama.cppextraction | 2026-08-26 |
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 (3)
| Finished | Suite | Runtime · profile | Score | Coverage | Grader · dataset · config |
|---|---|---|---|---|---|
| nullschemanullschema/1 | llama.cppextraction | 45.8% | Coverage 72/72 | g d7448e0f5fc3f9afd 3b91280bb40372efc 5e7cd3243c74ce98 | |
| screeningscreening/1 | llama.cppextraction | 88.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 45dab17de7814804 | |
| groundinggrounding/1 | llama.cppextraction | 80.8% | Coverage 125/125 | g 30b933dcc6a7e2d4d dcb396faf8b83b0ac b3059734754cd76c |
- Qwen3 Coder 30BMeasured, not seated
30B · MoE · Q4_K_M · 18.0 GB
The first coding model measured against a real coding contract rather than an extraction suite.
- Qwen3.6 35B-A3BMeasured, not seated
35B · MoE · MLX 4-bit (also held as UD-Q5_K_M GGUF) · 19.0 GB
Tested as the fast general MoE, and used as the daily coding driver in DSH. Moved to an MLX build on 2026-09-09.
- Qwen3.8 27BSeated · agentic
27B · dense · MLX 4-bit (MTP build, template patched to reasoning_effort=medium) · 15.0 GB
The dense counterweight to the MoE fleet, and the model where MLX first beat llama.cpp. Promoted to the agent seat on 2026-09-09 after toolcall/1.
- Qwen3.8-Flash-NextRemoved
180B · MoE · AD-3.84bpw M64 · 79.1 GB
Tested because the M64 shard layout claims to run a 180B model on 64GB by keeping a 51B n-gram embedding table on SSD.