---
title: Tess-4-27B-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Tess-4-27B-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Tess-4-27B-8bit.md"
repository: mlx-community/Tess-4-27B-8bit
last_updated: 2026-07-10
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
base_model:
  - migtissera/Tess-4-27B
base_model_relation: quantized
parameters: 8.0B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 42
stars: 0
tags:
  - tess
  - agentic
  - reasoning
  - thinking
  - long-context
  - tool-use
  - qwen3
  - multimodal
  - mlx
---

# Tess-4-27B-8bit

> Tess-4-27B-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Tess-4-27B-8bit

mlx-community/Tess-4-27B-8bit 是 ModelScope 魔搭社区上的 8.0B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 migtissera/Tess-4-27B 构建。

- **Repository**: mlx-community/Tess-4-27B-8bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 8.0B
- **Base model**: migtissera/Tess-4-27B
- **Tags**: tess, agentic, reasoning, thinking, long-context, tool-use, qwen3, multimodal, mlx
- **Downloads**: 42
- **Stars**: 0
- **Last updated**: 2026-07-10

Source: https://www.modelscope.cn/models/mlx-community/Tess-4-27B-8bit

---

# mlx-community/Tess-4-27B-8bit

This model was converted to MLX format from [`migtissera/Tess-4-27B`](https://huggingface.co/migtissera/Tess-4-27B)
using mlx-vlm version **0.6.4**.
Refer to the [original model card](https://huggingface.co/migtissera/Tess-4-27B) for more details on the model.

## Use with mlx

```bash
pip install -U mlx-vlm
```

```bash
python -m mlx_vlm.generate --model mlx-community/Tess-4-27B-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```