Downloads · 30 days
9
17% of all-time downloads
BlivionIaG/Qwen3.5-0.8B-exl3-3.0bpw
Qwen3.5-0.8B-exl3-3.0bpw is a image-text-to-text model from BlivionIaG. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Qwen3.5-0.8B quantized to 3.0 bits-per-weight with the EXL3 (bitshift trellis) format, using the 3inst codebook.
Downloads · 30 days
9
17% of all-time downloads
All-time downloads
53
Public
Parameters
445M
903 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors890 MB · 97%
How the weights are stored.
BF16255M · 57%
From the Hugging Face model README
Qwen3.5-0.8B quantized to 3.0 bits-per-weight with the EXL3 (bitshift trellis) format, using the 3inst codebook.
Quantized with exllamav3.
This is an EXL3-format quantization of Qwen/Qwen3.5-0.8B, the lightweight vision-language variant of the Qwen3.5 family. See the base model card for architecture details, intended use, and limitations.
| Property | Value |
|---|---|
| Base model | Qwen/Qwen3.5-0.8B |
| Quantization format | EXL3 (QTIP-style bitshift trellis) |
| Bits per weight | 3.0 (head: 6.0) |
| Codebook | 3inst |
| Parameters | ~0.8B |
| License | Apache 2.0 |
| Metric | fp16 | 3.0bpw EXL3 | Delta |
|---|---|---|---|
| Perplexity (Wiki) | 11.21 | 12.24 | +9.2% |
| KL div (fp16 || 3bit) | — | 0.101 | — |
| Top-1 accuracy | 0.525 | 0.512 | −2.5pp |
This repository is intended for use with EXL3-capable inference runtimes (ExLlamaV3). It is not a standalone Transformers-format model.
# ExLlamaV3
python chat.py -m BlivionIaG/Qwen3.5-0.8B-exl3-3.0bpw
This is a community quantization; the base model's capabilities and limitations apply unchanged.