---
title: AceReason-Nemotron-7B-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/AceReason-Nemotron-7B-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/AceReason-Nemotron-7B-8bit.md"
repository: mlx-community/AceReason-Nemotron-7B-8bit
last_updated: 2025-05-26
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - nvidia/AceReason-Nemotron-7B
base_model_relation: quantized
parameters: 2.1B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 290
stars: 0
tags:
  - nvidia
  - reasoning
  - math
  - code
  - "reinforcement learning"
  - pytorch
  - mlx
---

# AceReason-Nemotron-7B-8bit

> AceReason-Nemotron-7B-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/AceReason-Nemotron-7B-8bit

mlx-community/AceReason-Nemotron-7B-8bit 是 ModelScope 魔搭社区上的 2.1B 参数text-generation模型，采用 other 许可，基于 nvidia/AceReason-Nemotron-7B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/AceReason-Nemotron-7B-8bit
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 2.1B
- **Base model**: nvidia/AceReason-Nemotron-7B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: nvidia, reasoning, math, code, reinforcement learning, pytorch, mlx
- **Downloads**: 290
- **Stars**: 0
- **Last updated**: 2025-05-26

Source: https://www.modelscope.cn/models/mlx-community/AceReason-Nemotron-7B-8bit

---

# mlx-community/AceReason-Nemotron-7B-8bit

This model [mlx-community/AceReason-Nemotron-7B-8bit](https://huggingface.co/mlx-community/AceReason-Nemotron-7B-8bit) was
converted to MLX format from [nvidia/AceReason-Nemotron-7B](https://huggingface.co/nvidia/AceReason-Nemotron-7B)
using mlx-lm version **0.24.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/AceReason-Nemotron-7B-8bit")

prompt = "hello"

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

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