---
title: Arete-27B-OptiQ-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Arete-27B-OptiQ-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Arete-27B-OptiQ-4bit.md"
repository: mlx-community/Arete-27B-OptiQ-4bit
last_updated: 2026-11-11
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
base_model:
  - NousResearch/Arete-27B
base_model_relation: quantized
parameters: 5.7B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 25
stars: 0
tags:
  - mlx
  - optiq
  - quantized
  - 4bit
  - mixed-precision
  - qwen3.8
  - nous-research
  - arete
  - reasoning
  - multimodal
  - vision
  - image-text-to-text
  - long-context
  - function-calling
  - tool-use
  - apple-silicon
---

# Arete-27B-OptiQ-4bit

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

mlx-community/Arete-27B-OptiQ-4bit 是 ModelScope 魔搭社区上的 5.7B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 NousResearch/Arete-27B 构建。

- **Repository**: mlx-community/Arete-27B-OptiQ-4bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 5.7B
- **Base model**: NousResearch/Arete-27B
- **Tags**: mlx, optiq, quantized, 4bit, mixed-precision, qwen3.8, nous-research, arete, reasoning, multimodal, vision, image-text-to-text, long-context, function-calling, tool-use, apple-silicon
- **Downloads**: 25
- **Stars**: 0
- **Last updated**: 2026-11-11

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

---

# mlx-community/Arete-27B-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 and no cloud. [All OptiQ quants](https://mlx-optiq.com/models) · [Docs](https://mlx-optiq.com/docs/)

OptiQ mixed-precision quant of [NousResearch/Arete-27B](https://huggingface.co/NousResearch/Arete-27B), Nous Research's supervised fine-tune of Qwen3.8-27B. Nous trained it to answer politically sensitive questions factually instead of refusing or deflecting. It is a Qwen3.8-family vision-language model. 20 GB on disk.

## What it is

| Property | Value |
|---|---|
| Base | NousResearch/Arete-27B (Qwen3.8, 27B) |
| Method | OptiQ mixed-precision, per-layer 4/8-bit |
| Bit allocation | Reused from the [Qwen3.8-27B OptiQ recipe](https://huggingface.co/mlx-community/Qwen3.8-27B-OptiQ-4bit): the architecture is identical, so the per-layer sensitivity ranking transfers directly and no per-model sweep is needed |
| Layer split | 237 components at 4-bit, 261 at 8-bit |
| Group size | 64 |
| On disk | 20 GB |
| Vision | bf16 vision tower kept in `optiq_vision.safetensors` for image input |
| KV cache | Mixed-precision KV config in `kv_config.json` |
| MTP | None: the Arete release does not include the speculation head |

Following the naming `llama.cpp` uses for its mixed quants, the "4bit" label denotes the family, not the weighted average.

## Run it

```bash
pip install mlx-optiq
```

```python
import optiq  # registers the arch + vision sidecar
from mlx_lm import load, generate

model, tok = load("mlx-community/Arete-27B-OptiQ-4bit")
prompt = tok.apply_chat_template(
    [{"role": "user", "content": "Explain mixed-precision quantization in two sentences."}],
    tokenize=False, add_generation_prompt=True,
)
print(generate(model, tok, prompt=prompt, max_tokens=400))
```

For image input plus an OpenAI- and Anthropic-compatible endpoint with mixed-precision KV cache:

```bash
optiq serve --model mlx-community/Arete-27B-OptiQ-4bit
```

This is a reasoning model, so give it a generous token budget.

## Links

- **Project website:** [mlx-optiq.com](https://mlx-optiq.com/)
- **All OptiQ quants:** [mlx-optiq.com/models](https://mlx-optiq.com/models)
- **Base model:** [NousResearch/Arete-27B](https://huggingface.co/NousResearch/Arete-27B)