- Parameters
- 30B
- Quant
- Q4_K_M
- Size
- 16.5 GB
- Family
- granite
granite-4.2-30b-gguf
Measured, not seateddenseresidentllama.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 because IBM builds explicitly for structured JSON output, and nullschema is the weakest axis across the whole fleet.
What came of it
Second-best abstention on the board at 90.3% nullschema and 98.3% screening, from 16.5GB and Apache 2.0. Schema enforcement verified directly. At 9.0 tok/s it is a batch extraction candidate only, never an agentic one. Its KV is the most expensive measured here: 30.26 GB at 131k, taking it to 48.62 GB and past the memory budget. Strong at 8k to 32k, unusable at its full window.
| Suite | Score | 95% interval | Passed | Runtime · profile | Recorded |
|---|---|---|---|---|---|
| grounding | 84.0% | 76.6–89.4 | Passed 105/125 | llama.cppextraction | 2026-09-08 |
| nullschema | 90.3% | 81.3–95.2 | Passed 65/72 | llama.cppextraction | 2026-09-08 |
| screening | 98.3% | 91.1–99.7 | Passed 59/60 | llama.cppextraction | 2026-09-08 |
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 | 90.3% | Coverage 72/72 | g d7448e0f5fc3f9afd 3b91280bb40372efc ad5177ffa2d55fa5 | |
| groundinggrounding/1 | llama.cppextraction | 84.0% | Coverage 125/125 | g 30b933dcc6a7e2d4d dcb396faf8b83b0ac e353f603986dcdcd | |
| screeningscreening/1 | llama.cppextraction | 98.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 001987450ecbaa8a |
- Granite Guardian 4.1 8BSeated · Screen
8B · dense · Q4_K_M GGUF, and MLX mixed_3_6 at 3.8GB · 5.1 GB
A purpose-built safety and screening classifier, tested for the judge seat where a general model was overkill.