Qwen3.5 · 0.8B
EXL3 · 3.0 bpw · 1.0 GB · Dense
[!NOTE] An ExLlamaV3 build of
Qwen/Qwen3.5-0.8Bat 3.0 bits per weight. See Quants for sibling repos at other bit‑widths or browse the collection.
Quants
| BPW | Mode | Size | median KL self-sampled |
Status |
|---|---|---|---|---|
| 3.0 | plain | 1.0 GB | 1.64e-04 | link |
| 3.0 | SC H6 V6 | 1.0 GB | 4.35e-05 | this repo |
| 4.0 | plain | 1.1 GB | — | link |
Inference
| Loader | Use it for |
|---|---|
| TabbyAPI | OpenAI‑compatible HTTP server. Drop‑in for OpenAI clients. |
| text‑generation‑webui | Local chat UI. Pick the ExLlamaV3 loader from the model dropdown. |
| ExLlamaV3 | Direct Python API for embedding the model in your own code or pipeline. |
Download
pip install -U huggingface_hub
hf download \
Honkware/Qwen3.5-0.8B-exl3-SC-3.0bpw-H6-V6 \
--local-dir ./Qwen3.5-0.8B-exl3-SC-3.0bpw-H6-V6
quantization_config.json)| Setting | Value |
|---|---|
| Format | EXL3 |
| Bits per weight | 3.0 |
| Head bits | 6 |
| Calibration rows | 250 |
| Calibration data | exllamav3 bundled mix (c4, code, multilingual, technical, tiny, wiki) |
| Codebook | mul1 |
| Out‑scales | always |
| Parallel mode | enabled |
| Vision tower | 6 bits |
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.
Quantized with BlockQuant · convention
{org}/{model}-exl3-{bpw}bpw