---
title: DeepSeek-V4-Flash-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-V4-Flash-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-V4-Flash-8bit.md"
repository: mlx-community/DeepSeek-V4-Flash-8bit
last_updated: 2026-04-26
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - deepseek_v4
architectures:
  - DeepseekV4ForCausalLM
parameters: 45.4B
tensor_type:
  - U32
  - F32
  - I64
  - U8
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 198
stars: 1
tags:
  - mlx
---

# DeepSeek-V4-Flash-8bit

> DeepSeek-V4-Flash-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/DeepSeek-V4-Flash-8bit

- **Repository**: mlx-community/DeepSeek-V4-Flash-8bit
- **Tasks**: text-generation
- **Parameters**: 45.4B
- **Tags**: mlx
- **Downloads**: 198
- **Stars**: 1
- **Last updated**: 2026-04-26

Source: https://www.modelscope.cn/models/mlx-community/DeepSeek-V4-Flash-8bit

---

# mlx-community/DeepSeek-V4-Flash-8bit

Made possible by [Lambda.ai](https://huggingface.co/lambda) ❤️

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-V4-Flash-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, return_dict=False,
    )

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