---
title: ColGrep-Agent-2B-MLX-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/ColGrep-Agent-2B-MLX-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/ColGrep-Agent-2B-MLX-8bit.md"
repository: mlx-community/ColGrep-Agent-2B-MLX-8bit
last_updated: 2026-10-19
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - lightonai/colgrep-agent-2B
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 48
stars: 0
tags:
  - mlx
  - code-search
  - tool-use
  - apple-silicon
---

# ColGrep-Agent-2B-MLX-8bit

> ColGrep-Agent-2B-MLX-8bit - mlx-community 在 ModelScope 开源的模型。ColGrep-Agent-2B - MLX 8BIT

mlx-community/ColGrep-Agent-2B-MLX-8bit 是 ModelScope 魔搭社区上的text-generation模型，采用 apache-2.0 许可，基于 lightonai/colgrep-agent-2B 构建。

- **Repository**: mlx-community/ColGrep-Agent-2B-MLX-8bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Base model**: lightonai/colgrep-agent-2B
- **Tags**: mlx, code-search, tool-use, apple-silicon
- **Downloads**: 48
- **Stars**: 0
- **Last updated**: 2026-10-19

Source: https://www.modelscope.cn/models/mlx-community/ColGrep-Agent-2B-MLX-8bit

---

# ColGrep-Agent-2B - MLX 8BIT

Native Apple Silicon MLX conversion of [LightOn's ColGrep-Agent-2B](https://huggingface.co/lightonai/colgrep-agent-2B), a specialized repository code-localization agent built on MiniCPM5-2B.

- Upstream checkpoint: `lightonai/colgrep-agent-2B` at `f798a61129c6decb5166864e0a3c98373e62c764`
- Conversion: MLX-LM 0.32.0, 8-bit affine, group size 64
- Compatibility: source `chat_template.jinja` preserved; top-level `rope_theta=5000000` added so MLX-LM's Llama RoPE implementation matches the source configuration.
- Original model authors: LightOn AI; original model license: Apache-2.0.

## Usage

```bash
pip install 'mlx-lm==0.32.0' 'transformers>=5.6.2,<6'
mlx_lm.generate --model . --prompt 'Hello' --max-tokens 128
```

**This is not a general coding assistant.** It was trained for iterative code search with `colgrep`, `terminal`, and `finish`. Use the upstream chat template, system prompt, tool schemas, and thinking disabled. The official `colgrep --agent` CLI currently runs GGUF through llama.cpp; this MLX checkpoint is **not** a drop-in replacement for that CLI. An MLX-backed harness is separate integration work.

This checkpoint is not claimed to match upstream BF16 on benchmarks until an apples-to-apples evaluation of full search trajectories is reported. The smoke test validates basic load, format, and first tool-call structure only.

- Upstream blog: https://huggingface.co/blog/lightonai/colgrep-agent
- Upstream harness: https://github.com/lightonai/next-plaid
- MLX-LM: https://github.com/ml-explore/mlx-lm