Qwen3-VL-32B-Instruct-ultra-uncensored-heretic-GGUF
mradermacher/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic-GGUF
quantGGUFIQ4_XS
Published metrics
- KL divergence
- 0.042
- Refusals
- 4/100
- Original refusals
- 99/100
- Heretic version
- —
Inherited from the parent conversion — source
Matched snippet
| KL divergence | 0.0421 | | Refusals | 4/100 |
Provenance
- Canonical model
- Qwen/Qwen3-VL-32B-Instruct
- Declared parent(s)
- llmfan46/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic
- Classification
- quantized artifact of a Heretic model
- Created / updated
- 2026-04-17 / 2026-10-07
- Downloads
- 16.3K all time · 2.1K last 30 days
- License
- apache-2.0
Refusal rate 4%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.