---
title: Qwopus3.6-27B-Coder-oQ4-mtp
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwopus3.6-27B-Coder-oQ4-mtp"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwopus3.6-27B-Coder-oQ4-mtp.md"
repository: mlx-community/Qwopus3.6-27B-Coder-oQ4-mtp
last_updated: 2026-09-16
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
parameters: 4.9B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 24
stars: 0
tags:
  - mlx
  - oq
  - quantized
---

# Qwopus3.6-27B-Coder-oQ4-mtp

> Qwopus3.6-27B-Coder-oQ4-mtp - mlx-community 在 ModelScope 开源的模型。Qwopus3.6-27B-Coder-oQ4-mtp

- **Repository**: mlx-community/Qwopus3.6-27B-Coder-oQ4-mtp
- **Parameters**: 4.9B
- **Tags**: mlx, oq, quantized
- **Downloads**: 24
- **Stars**: 0
- **Last updated**: 2026-09-16

Source: https://www.modelscope.cn/models/mlx-community/Qwopus3.6-27B-Coder-oQ4-mtp

---

# Qwopus3.6-27B-Coder-oQ4-mtp

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.7.0.dev2) mixed-precision quantization.

## Quantization details

- **Model type**: qwen3_5
- **Bits**: 4
- **Group size**: 64
- **Format**: MLX safetensors