Swift-Qwen3.8-27b EXL3
Collection
EXL3 quants of Swift-Qwen3.8-27b, produced by BlockQuant. โข 1 item โข Updated
An ExLlamaV3 build of
ukisai/Swift-Qwen3.8-27bat 4.0 bits per weight. See Quants for sibling repos at other bitโwidths or browse the collection.
| BPW | Size | median KL wiki2 |
Status |
|---|---|---|---|
| 4.0 | 16.4 GB | 0.0080 | this repo |
| Loader | Use it for |
|---|---|
| TabbyAPI | OpenAIโcompatible HTTP server. Dropโin for OpenAI clients. |
| textโgenerationโwebui | 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. |
pip install -U huggingface_hub
hf download \
Honkware/Swift-Qwen3.8-27b-exl3-4.0bpw \
--local-dir ./Swift-Qwen3.8-27b-exl3-4.0bpw
quantization_config.json)| Setting | Value |
|---|---|
| Format | EXL3 |
| Bits per weight | 4.0 |
| Head bits | 5 |
| Calibration rows | 250 |
| Calibration data | exllamav3 bundled mix (c4, code, multilingual, technical, tiny, wiki) |
| Codebook | mul1 |
| Outโscales | always |
| Parallel mode | enabled |
Use and license follow the base model. Quantization adds no additional restrictions. Refer to the upstream repository for terms, citation, and safety documentation.
{org}/{model}-exl3-{bpw}bpw