Qwen3-VL-32B-Instruct-heretic-v2-Q4_K_M-GGUF
n0kovo/Qwen3-VL-32B-Instruct-heretic-v2-Q4_K_M-GGUF
quantGGUFF16
Published metrics
- KL divergence
- 0.157
- Refusals
- 7/100
- Original refusals
- 99/100
- Heretic version
- —
Inherited from the parent conversion — source
Matched snippet
| KL divergence | 0.1565 | | Refusals | 7/100 |
Provenance
- Canonical model
- Qwen/Qwen3-VL-32B-Instruct
- Declared parent(s)
- n0kovo/Qwen3-VL-32B-Instruct-heretic-v2
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2025-12-16 / 2025-12-16
- Downloads
- 6.6K all time · 303 last 30 days
- License
- apache-2.0
Refusal rate 7%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.