Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-NM-DAU-UltraOptimised-VariableThinking-GGUF
Solstice-AI/Qwen3.8-27B-TTURBO-Cold-Fusion-709-L-NM-DAU-UltraOptimised-VariableThinking-GGUF
finetuneGGUFIQ4_XS
Published metrics
- KL divergence
- 0.053
- Refusals
- 0/100
- Original refusals
- 99/100
- Heretic version
- v1.2.0
Published on the model card
Matched snippet
| KL divergence | 0.0535 | | Refusals | 0/100 |
Provenance
- Canonical model
- Qwen/Qwen3.8-27B
- Declared parent(s)
- DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored
- Classification
- card identifies this as a finetune of a Heretic model
- Created / updated
- 2026-09-11 / 2026-10-15
- Downloads
- 6.4K all time · 2K last 30 days
- License
- apache-2.0
Refusal rate 0%. Metrics are self-reported by the publisher; the directory does not re-run evaluations.