Huihui-Qwen3.8-27B-abliterated-GGUF
This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
Params
27.0 B
Context
—
Downloads 30d
3.9 M
Likes
1,886
Download history
daily snapshots · 79 days
▲ 1.7 M in the last 30 days (80.8%)
3.9 M2.2 M
Oct 12Oct 22Nov 1Nov 10
3.9 M943 K
Aug 24Sep 19Oct 15Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| Huihui-Qwen3.8-27B-abliterated-Q2_K.gguf | Q2_K | 10.9 GB | 16.5 GB | ✅ Runs comfortably |
| Huihui-Qwen3.8-27B-abliterated-UD-DW-IQ3_XXS.gguf | IQ3_XXS | 11.4 GB | 17.1 GB | ✅ Runs comfortably |
| Huihui-Qwen3.8-27B-abliterated-UD-DW-IQ3_S.gguf | IQ3_S | 12.3 GB | 18.1 GB | ✅ Runs comfortably |
| Huihui-Qwen3.8-27B-abliterated-Q3_K.gguf | Q3_K | 13.5 GB | 19.4 GB | ✅ Runs comfortably |
| Huihui-Qwen3.8-27B-abliterated-Q4_K.gguf | Q4_K | 16.8 GB | 23.0 GB | ⚠️ Tight — reduce context |
| Huihui-Qwen3.8-27B-abliterated-Q2_K_L.gguf | Q2_K_L | 17.2 GB | 23.5 GB | ⚠️ Tight — reduce context |
| Huihui-Qwen3.8-27B-abliterated-Q3_K_L.gguf | Q3_K_L | 18.7 GB | 25.1 GB | ❌ Won’t fit |
| Huihui-Qwen3.8-27B-abliterated-Q4_K_L.gguf | Q4_K_L | 20.9 GB | 27.6 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 27.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-08-16
- Base model
- Qwen3.8-27B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-24
Compare with any image-text-to-text model
Popular comparisons
Appears in