license: apache-2.0 base_model: huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated base_model_relation: quantized quantized_by: blockblockblock library_name: exllamav3 pipeline_tag: text-generation tags:
- exl3
- exllamav3
- quantized
quantization_format: exl3 bits_per_weight: 5.0
Huihui · Qwen3.6 · 35B · A3B · Claude · 4.7 · Opus · abliterated
EXL3 · 5.0 bpw · 23.7 GB · Dense
base model quantized by collection
[!NOTE] An ExLlamaV3 build of
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliteratedat 5.0 bits per weight. See Quants for sibling repos at other bit‑widths or browse the collection.
Quants
| BPW | Head bits | Calibration rows | Size | Status |
|---|---|---|---|---|
| 3.0 | 8 | 250 | 15.3 GB | link |
| 4.0 | 8 | 250 | 19.5 GB | link |
| 4.5 | 8 | 250 | 21.6 GB | link |
| 5.0 | 8 | 250 | 23.7 GB | this repo |
| 6.0 | 8 | 250 | 27.9 GB | link |
Inference
Download
pip install -U huggingface_hub
hf download \
blockblockblock/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-exl3-5.0bpw \
--local-dir ./Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-exl3-5.0bpw
| Setting | Value |
|---|---|
| Format | EXL3 |
| Bits per weight | 5.0 |
| Head bits | 8 |
| Calibration rows | 250 |
| Codebook | MCG |
| Out‑scales | always |
| Parallel mode | enabled |
Loaded automatically by every ExLlamaV3 loader; reproduced here for searchability.
License & use
[!IMPORTANT] Use and license follow the base model. Quantization adds no additional restrictions. Refer to the upstream repository for terms, citation, and safety documentation.