- Parameters
- 30B / 3B active
- Quant
- Q4_K_M
- Size
- 24.0 GB
- Family
- nemotron
RecordStatus · runtime · seat
nemotron-lightning-30b
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
Tested as a fast MoE, 45.9 tok/s, and briefly the best raw scorer on some suites.
What came of it
Deleted. 15.3% nullschema through llama.cpp and 9.7% through MLX, the worst abstention measured. Fast and confident is the wrong combination for extraction.
Recorded runs3 scored · 95% intervals
| Suite | Score | 95% interval | Passed | Runtime · profile | Recorded |
|---|---|---|---|---|---|
| grounding | 60.0% | 51.2–68.2 | Passed 75/125 | llama.cppextraction | 2026-09-05 |
| nullschema | 15.3% | 8.8–25.3 | Passed 11/72 | llama.cppextraction | 2026-09-05 |
| screening | 93.3% | 84.1–97.4 | Passed 56/60 | 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 (3)
| Finished | Suite | Runtime · profile | Score | Coverage | Grader · dataset · config |
|---|---|---|---|---|---|
| nullschemanullschema/1 | llama.cppextraction | 15.3% | Coverage 72/72 | g d7448e0f5fc3f9afd 3b91280bb40372efc 8f3225e9b30dcc6b | |
| screeningscreening/1 | llama.cppextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc bd58c270aedc9f3d | |
| groundinggrounding/1 | llama.cppextraction | 60.0% | Coverage 125/125 | g 30b933dcc6a7e2d4d dcb396faf8b83b0ac f734b41b3caabfdd |