---
title: 35b-beta-long-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/35b-beta-long-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/35b-beta-long-8bit.md"
repository: mlx-community/35b-beta-long-8bit
last_updated: 2024-12-20
license: gpl-3.0
model_type:
  - cohere
architectures:
  - CohereForCausalLM
parameters: 9.8B
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
  - ja
  - de
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 997
stars: 0
tags:
  - mlx
---

# 35b-beta-long-8bit

> 35b-beta-long-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/35b-beta-long-8bit

mlx-community/35b-beta-long-8bit 是 ModelScope 魔搭社区上的 9.8B 参数机器学习模型，采用 gpl-3.0 许可，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/35b-beta-long-8bit
- **License**: gpl-3.0
- **Parameters**: 9.8B
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 997
- **Stars**: 0
- **Last updated**: 2024-12-20

Source: https://www.modelscope.cn/models/mlx-community/35b-beta-long-8bit

---

# mlx-community/35b-beta-long-8bit

The Model [mlx-community/35b-beta-long-8bit](https://huggingface.co/mlx-community/35b-beta-long-8bit) was converted to MLX format from [CausalLM/35b-beta-long](https://huggingface.co/CausalLM/35b-beta-long) using mlx-lm version **0.12.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/35b-beta-long-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```