---
title: Hermes-4-70B-5bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Hermes-4-70B-5bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Hermes-4-70B-5bit.md"
repository: mlx-community/Hermes-4-70B-5bit
last_updated: 2025-08-27
license: llama3
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - NousResearch/Hermes-4-70B
base_model_relation: quantized
parameters: 13.2B
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: 91
stars: 0
tags:
  - Llama-3.1
  - instruct
  - finetune
  - reasoning
  - hybrid-mode
  - chatml
  - "function calling"
  - "tool use"
  - "json mode"
  - "structured outputs"
  - atropos
  - dataforge
  - "long context"
  - roleplaying
  - chat
  - mlx
---

# Hermes-4-70B-5bit

> Hermes-4-70B-5bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Hermes-4-70B-5bit

mlx-community/Hermes-4-70B-5bit 是 ModelScope 魔搭社区上的 13.2B 参数text-generation模型，采用 llama3 许可，基于 NousResearch/Hermes-4-70B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/Hermes-4-70B-5bit
- **License**: llama3
- **Tasks**: text-generation
- **Parameters**: 13.2B
- **Base model**: NousResearch/Hermes-4-70B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: Llama-3.1, instruct, finetune, reasoning, hybrid-mode, chatml, function calling, tool use, json mode, structured outputs, atropos, dataforge, long context, roleplaying, chat, mlx
- **Downloads**: 91
- **Stars**: 0
- **Last updated**: 2025-08-27

Source: https://www.modelscope.cn/models/mlx-community/Hermes-4-70B-5bit

---

# mlx-community/Hermes-4-70B-5bit

This model [mlx-community/Hermes-4-70B-5bit](https://huggingface.co/mlx-community/Hermes-4-70B-5bit) was
converted to MLX format from [NousResearch/Hermes-4-70B](https://huggingface.co/NousResearch/Hermes-4-70B)
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/Hermes-4-70B-5bit")

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)
```