---
base_model: Qwen/Qwen3.6-27B
tags:
- autoround
- intel
- gguf
- quantization
- mtp
license: apache-2.0
---

# Qwen3.6-27B MTP GGUF (AutoRound Quantized)

This repository contains a GGUF release of the **MTP** version of [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B), quantized with Intel's [AutoRound](https://github.com/intel/auto-round).

## Available Files

| File Name | Quant Type | Size |
|-----------|------------|------|
| `Qwen3.6-27B-ATR-Q2_K_S.gguf` | Q2_K_S | 9.67 GiB |
| `Qwen3.6-27B-ATR-Q2_K_MIXED.gguf` | Q2_K_S | 10.83 GiB |
| `Qwen3.6-27B-ATR-Q3_K_M.gguf` | Q3_K_M | 12.22 GiB |
| `Qwen3.6-27B-ATR-Q4_K_M.gguf` | Q4_K_M | 15.65 GiB |
| `Qwen3.6-27B-ATR-Q5_K_M.gguf` | Q5_K_M | 18.19 GiB |

## Notes

- More quantizations may be added later.