---
title: chandra-ocr-2-oQ8
canonical_url: "https://www.modelscope.cn/models/mlx-community/chandra-ocr-2-oQ8"
md_url: "https://www.modelscope.cn/models/mlx-community/chandra-ocr-2-oQ8.md"
repository: mlx-community/chandra-ocr-2-oQ8
last_updated: 2026-07-10
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
parameters: 1.5B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 28
stars: 0
tags:
  - mlx
  - oq
  - quantized
---

# chandra-ocr-2-oQ8

> chandra-ocr-2-oQ8 - mlx-community 在 ModelScope 开源的模型。This model was quantized using oQ (oMLX v0.3.7) mixed-precision quantization.

- **Repository**: mlx-community/chandra-ocr-2-oQ8
- **Parameters**: 1.5B
- **Tags**: mlx, oq, quantized
- **Downloads**: 28
- **Stars**: 0
- **Last updated**: 2026-07-10

Source: https://www.modelscope.cn/models/mlx-community/chandra-ocr-2-oQ8

---

# chandra-ocr-2-oQ8

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.7) mixed-precision quantization.

## Quantization details

- **Model type**: qwen3_5
- **Bits**: 8
- **Group size**: 64
- **Format**: MLX safetensors