---
title: Mistral-Nemo-Instruct-2407-3bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Mistral-Nemo-Instruct-2407-3bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Mistral-Nemo-Instruct-2407-3bit.md"
repository: mlx-community/Mistral-Nemo-Instruct-2407-3bit
last_updated: 2025-02-06
license: apache-2.0
model_type:
  - mistral
architectures:
  - MistralForCausalLM
base_model:
  - mistralai/Mistral-Nemo-Instruct-2407
base_model_relation: quantized
parameters: 1.5B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ru
  - zh
  - ja
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 710
stars: 0
tags:
  - mlx
---

# Mistral-Nemo-Instruct-2407-3bit

> Mistral-Nemo-Instruct-2407-3bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Mistral-Nemo-Instruct-2407-q3

mlx-community/Mistral-Nemo-Instruct-2407-3bit 是 ModelScope 魔搭社区上的 1.5B 参数机器学习模型，采用 apache-2.0 许可，基于 mistralai/Mistral-Nemo-Instruct-2407 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Mistral-Nemo-Instruct-2407-3bit
- **License**: apache-2.0
- **Parameters**: 1.5B
- **Base model**: mistralai/Mistral-Nemo-Instruct-2407
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 710
- **Stars**: 0
- **Last updated**: 2025-02-06

Source: https://www.modelscope.cn/models/mlx-community/Mistral-Nemo-Instruct-2407-3bit

---

# mlx-community/Mistral-Nemo-Instruct-2407-q3

The Model [mlx-community/Mistral-Nemo-Instruct-2407-q3](https://huggingface.co/mlx-community/Mistral-Nemo-Instruct-2407-q3) was
converted to MLX format from [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)
using mlx-lm version **0.20.5**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mistral-Nemo-Instruct-2407-q3")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```