---
title: KAT-Coder-V2.5-Dev-OptiQ-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit.md"
repository: mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit
last_updated: 2026-09-15
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_5_moe
architectures:
  - Qwen3_5MoeForConditionalGeneration
base_model:
  - Kwaipilot/KAT-Coder-V2.5-Dev
base_model_relation: quantized
parameters: 6.0B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 98
stars: 1
tags:
  - mlx
  - optiq
  - code
---

# KAT-Coder-V2.5-Dev-OptiQ-4bit

> KAT-Coder-V2.5-Dev-OptiQ-4bit - mlx-community 在 ModelScope 开源的模型。KAT-Coder-V2.5-Dev-OptiQ-4bit

mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit 是 ModelScope 魔搭社区上的 6.0B 参数text-generation模型，采用 apache-2.0 许可，基于 Kwaipilot/KAT-Coder-V2.5-Dev 构建。

- **Repository**: mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 6.0B
- **Base model**: Kwaipilot/KAT-Coder-V2.5-Dev
- **Tags**: mlx, optiq, code
- **Downloads**: 98
- **Stars**: 1
- **Last updated**: 2026-09-15

Source: https://www.modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit

---

# KAT-Coder-V2.5-Dev-OptiQ-4bit

> **Built with [mlx-optiq](https://mlx-optiq.com)**, the MLX-native toolkit to
> quantize, fine-tune, and serve LLMs locally on Apple Silicon (no PyTorch, no
> cloud). [Try the Lab](https://mlx-optiq.com/docs/lab/) · [All OptiQ
> quants](https://mlx-optiq.com/models) · [Docs](https://mlx-optiq.com/docs/)

An [OptiQ](https://mlx-optiq.com) mixed-precision MLX quant of
**KAT-Coder-V2.5-Dev**, a `qwen3_5_moe` coding model (256-routed-expert sparse
MoE with hybrid linear + full attention).

- **Mixed 4/8-bit `static` build** — per-layer bit-widths assigned to a 4.5
  target bits-per-weight: 400 projections at 4-bit, 111 at 8-bit.
- **~4.51 bits per weight**, 20 GB on disk.

## Requirements

```bash
pip install -U optiq
```

`qwen3_5_moe` loads under stock `mlx-lm` too, but `optiq serve` adds mixed-
precision loading, KV-cache quantization, and the OptiQ Lab.

## Running it

```bash
optiq serve --model mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit
```

Then use the OpenAI-compatible endpoint at `http://localhost:8000/v1`, the
[OptiQ Lab](https://mlx-optiq.com/docs/lab/), or point `optiq code` at it. This
is a reasoning coder — it thinks before it answers.