- Parameters
- 35B / 3B active
- Quant
- Q6_K
- Size
- 29.0 GB
- Family
- ornith
RecordStatus · runtime · seat
ornith-1.5-35b-q6-b10618
Measured, not seatedMoEresidentllama.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
A second non-Qwen coding candidate, tested alongside Devstral.
What came of it
34.7% nullschema is poor, but it is being judged on extraction rather than code. 28.5 tok/s under MLX. Its verdict should be considered pending until a real coding suite runs.
Recorded runs3 scored · 95% intervals
| Suite | Score | 95% interval | Passed | Runtime · profile | Recorded |
|---|---|---|---|---|---|
| grounding | 72.8% | 64.4–79.8 | Passed 91/125 | llama.cppextraction | 2026-08-25 |
| nullschema | 34.7% | 24.8–46.2 | Passed 25/72 | llama.cppextraction | 2026-08-25 |
| screening | 95.0% | 86.3–98.3 | Passed 57/60 | llama.cppextraction | 2026-08-25 |
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 | 34.7% | Coverage 72/72 | g d7448e0f5fc3f9afd 3b91280bb40372efc 355fd8b860ca54b1 | |
| screeningscreening/1 | llama.cppextraction | 95.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc ce44f5f606a0131e | |
| groundinggrounding/1 | llama.cppextraction | 72.8% | Coverage 125/125 | g 30b933dcc6a7e2d4d dcb396faf8b83b0ac bc2f7777482c6fb6 |