---
title: EuroLLM-22B-Instruct-Preview-mlx-fp16
canonical_url: "https://www.modelscope.cn/models/mlx-community/EuroLLM-22B-Instruct-Preview-mlx-fp16"
md_url: "https://www.modelscope.cn/models/mlx-community/EuroLLM-22B-Instruct-Preview-mlx-fp16.md"
repository: mlx-community/EuroLLM-22B-Instruct-Preview-mlx-fp16
last_updated: 2025-08-22
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - utter-project/EuroLLM-22B-Instruct-Preview
base_model_relation: finetune
parameters: 22.6B
tensor_type:
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 104
stars: 0
tags:
  - mlx
  - mlx-my-repo
---

# EuroLLM-22B-Instruct-Preview-mlx-fp16

> EuroLLM-22B-Instruct-Preview-mlx-fp16 - mlx-community 在 ModelScope 开源的模型。mlx-community/EuroLLM-22B-Instruct-Preview-mlx-fp16

mlx-community/EuroLLM-22B-Instruct-Preview-mlx-fp16 是 ModelScope 魔搭社区上的 22.6B 参数text-generation模型，基于 utter-project/EuroLLM-22B-Instruct-Preview 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/EuroLLM-22B-Instruct-Preview-mlx-fp16
- **Tasks**: text-generation
- **Parameters**: 22.6B
- **Base model**: utter-project/EuroLLM-22B-Instruct-Preview
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx, mlx-my-repo
- **Downloads**: 104
- **Stars**: 0
- **Last updated**: 2025-08-22

Source: https://www.modelscope.cn/models/mlx-community/EuroLLM-22B-Instruct-Preview-mlx-fp16

---

# mlx-community/EuroLLM-22B-Instruct-Preview-mlx-fp16

The Model [mlx-community/EuroLLM-22B-Instruct-Preview-mlx-bf16](https://huggingface.co/mlx-community/EuroLLM-22B-Instruct-Preview-mlx-bf16) was converted to MLX format from [utter-project/EuroLLM-22B-Instruct-Preview](https://huggingface.co/utter-project/EuroLLM-22B-Instruct-Preview) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("bibproj/EuroLLM-22B-Instruct-Preview-mlx-fp16")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

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