Views
No views yet
[!Note] This repository contains model weights for the unofficial LQ8 quantizations of Qwen3.5 2B.LQ8 is an experimental quantization technique that is still in early beta, designed to provide fp16-level quality with the same or lower memory footprint as Q8_0.LQ8 is currently compatible with llama.cpp and Ollama out of the box. Please create a discussion if you find a bug.
| File Name | Quant Type | Bit Depth | Size | Download Link |
|---|---|---|---|---|
model-LQ8.gguf | LQ8 | ~8 bpw | 1.82 GB | 📥 Download LQ8 |