Model profile
Qwen3.6 27B
Evidence summary
Safety. Qwen3.6 27B has an estimated Safety rank of #107; its 90% source-sensitivity interval is #18–#246. Its behavior-only rank is #97; company governance moves the combined estimate to #107. Published Safety evidence spans 4 eval lineages and 5 of 7 components. Its strongest relative result is KIDBench Implicit Child Cue (implicit_child_cue_total_mean, #2 of 13); its weakest is ODCV-Bench (misalignment_rate, #10 of 12).
Freedom. Qwen3.6 27B has an estimated Freedom rank of #383; its 90% source-sensitivity interval is #179–#572. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is UGI Leaderboard — base-model willingness (willingness_direct_score, #66 of 156); its weakest is UGI Leaderboard — base-model willingness (willingness_adherence_score, #79 of 156).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-6-27b
- Hugging Face ↗Qwen/Qwen3.6-27B
- OpenRouter ↗qwen/qwen3.6-27b
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
- AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 ↗Direct non-quantized finetune documented by Hugging Face metadata
darkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic ↗Direct non-quantized finetune documented by Hugging Face metadata- DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP ↗Direct non-quantized finetune documented by Hugging Face metadata
dealignai/Qwen3.6-27B-JANG_4M-CRACK ↗Direct non-quantized finetune documented by Hugging Face metadata- dealignai/Qwen3.6-27B-MXFP4-CRACK-MTP ↗Direct non-quantized finetune documented by Hugging Face metadata
- dealignai/Qwen3.6-27B-MXFP8-CRACK-MTP ↗Direct non-quantized finetune documented by Hugging Face metadata
huihui-ai/Huihui-Qwen3.6-27B-abliterated ↗Direct non-quantized finetune documented by Hugging Face metadata
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #74 / 345 | ↓0.4927 | Source ↗official | |
| Governance Decay under Passive Context Compactiongovernance_retention_score | #4 / 7 | ↑70 | Source ↗official | |
| KIDBench Implicit Child Cueimplicit_child_cue_total_mean | #2 / 13 | ↑4.29 | Source ↗official | |
| ODCV-Benchaverage_severity | #9 / 12 | ↓1.669 | Source ↗official | |
| ODCV-Benchmisalignment_rate | #10 / 12 | ↓43.75 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| UGI Leaderboard — base-model willingnesswillingness_adherence_score | #79 / 156 | ↑1.5 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_direct_score | #66 / 156 | ↑3.5 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.