---
title: command-a-reasoning-08-2025
canonical_url: "https://www.modelscope.cn/models/mlx-community/command-a-reasoning-08-2025"
md_url: "https://www.modelscope.cn/models/mlx-community/command-a-reasoning-08-2025.md"
repository: mlx-community/command-a-reasoning-08-2025
last_updated: 2025-08-25
license: cc-by-nc-4.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - cohere2
architectures:
  - Cohere2ForCausalLM
base_model:
  - CohereLabs/command-a-reasoning-08-2025
base_model_relation: finetune
parameters: 111.1B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ja
  - ko
  - zh
  - ar
  - el
  - fa
  - pl
  - id
  - cs
  - he
  - hi
  - nl
  - ro
  - ru
  - tr
  - uk
  - vi
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 10
stars: 0
tags:
  - mlx
---

# command-a-reasoning-08-2025

> command-a-reasoning-08-2025 - mlx-community 在 ModelScope 开源的模型。mlx-community/command-a-reasoning-08-2025

mlx-community/command-a-reasoning-08-2025 是 ModelScope 魔搭社区上的 111.1B 参数text-generation模型，采用 cc-by-nc-4.0 许可，基于 CohereLabs/command-a-reasoning-08-2025 构建，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/command-a-reasoning-08-2025
- **License**: cc-by-nc-4.0
- **Tasks**: text-generation
- **Parameters**: 111.1B
- **Base model**: CohereLabs/command-a-reasoning-08-2025
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 10
- **Stars**: 0
- **Last updated**: 2025-08-25

Source: https://www.modelscope.cn/models/mlx-community/command-a-reasoning-08-2025

---

# mlx-community/command-a-reasoning-08-2025

This model [mlx-community/command-a-reasoning-08-2025](https://huggingface.co/mlx-community/command-a-reasoning-08-2025) was
converted to MLX format from [CohereLabs/command-a-reasoning-08-2025](https://huggingface.co/CohereLabs/command-a-reasoning-08-2025)
using mlx-lm version **0.26.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/command-a-reasoning-08-2025")

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)
```