---
title: c4ai-command-r-plus-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/c4ai-command-r-plus-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/c4ai-command-r-plus-8bit.md"
repository: mlx-community/c4ai-command-r-plus-8bit
last_updated: 2025-02-06
license: cc-by-nc-4.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - cohere
architectures:
  - CohereForCausalLM
parameters: 31.5B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ja
  - ko
  - zh
  - ar
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 986
stars: 0
tags:
  - mlx
---

# c4ai-command-r-plus-8bit

> c4ai-command-r-plus-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/c4ai-command-r-plus-8bit This model was converted to MLX format from CohereForAI/c4ai-command-r-plus using mlx-lm version 0.8.0. Refer to the original model card for more details on…

mlx-community/c4ai-command-r-plus-8bit 是 ModelScope 魔搭社区上的 31.5B 参数text-generation模型，采用 cc-by-nc-4.0 许可，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/c4ai-command-r-plus-8bit
- **License**: cc-by-nc-4.0
- **Tasks**: text-generation
- **Parameters**: 31.5B
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 986
- **Stars**: 0
- **Last updated**: 2025-02-06

Source: https://www.modelscope.cn/models/mlx-community/c4ai-command-r-plus-8bit

---

# mlx-community/c4ai-command-r-plus-8bit
This model was converted to MLX format from [`CohereForAI/c4ai-command-r-plus`]() using mlx-lm version **0.8.0**.
Refer to the [original model card](https://huggingface.co/CohereForAI/c4ai-command-r-plus) for more details on the model.
## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/c4ai-command-r-plus-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```