Views
No views yet
grug-9b-Q4_K_M. QAT = this rock.| test | old Q4 | QAT Q4 | change |
|---|---|---|---|
| HumanEval pass@1 % | 75.6 | 78.0 | +2.4 |
| MBPP pass@1 % | 75.0 | 74.0 | -1.0 |
| agent tool-call valid % | 61.1 | 88.9 | +27.8 |
| agent RIGHT tool % | 55.6 | 77.8 | +22.2 |
| agent reasoning present % | 100.0 | 100.0 | +0.0 |
| agent reasoning mean word | 7.1 | 5.8 | -1.3 |
<think>...</think>, normal say-word outside, XML tool call untouched. grug measure presence and length above, not merely hope.grug-9b-qat-Q4_K_M.gguf — about 5.6 GB. good default for 8 GB VRAM cave.llama-cli -hf ProCreations/grug-9b-qat-q4:Q4_K_M<think> tag and stay short on purpose. tool call use model XML format.ProCreations/grug-9bProCreations/grug-think