---
title: JOSIE-4B-Instruct-bfloat16
canonical_url: "https://www.modelscope.cn/models/mlx-community/JOSIE-4B-Instruct-bfloat16"
md_url: "https://www.modelscope.cn/models/mlx-community/JOSIE-4B-Instruct-bfloat16.md"
repository: mlx-community/JOSIE-4B-Instruct-bfloat16
last_updated: 2026-02-13
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
base_model:
  - Goekdeniz-Guelmez/JOSIE-4B-Instruct
base_model_relation: finetune
parameters: 1.4B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - multilingual
  - en
  - es
  - fr
  - pt
  - it
  - ar
  - ko
  - id
  - ru
  - vi
  - de
  - th
  - ja
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 15
stars: 0
tags:
  - chat
  - mlx
---

# JOSIE-4B-Instruct-bfloat16

> JOSIE-4B-Instruct-bfloat16 - mlx-community 在 ModelScope 开源的模型。mlx-community/JOSIE-4B-Instruct-bfloat16

mlx-community/JOSIE-4B-Instruct-bfloat16 是 ModelScope 魔搭社区上的 1.4B 参数text-generation模型，采用 mit 许可，基于 Goekdeniz-Guelmez/JOSIE-4B-Instruct 构建，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/JOSIE-4B-Instruct-bfloat16
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 1.4B
- **Base model**: Goekdeniz-Guelmez/JOSIE-4B-Instruct
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: chat, mlx
- **Downloads**: 15
- **Stars**: 0
- **Last updated**: 2026-02-13

Source: https://www.modelscope.cn/models/mlx-community/JOSIE-4B-Instruct-bfloat16

---

# mlx-community/JOSIE-4B-Instruct-bfloat16

This model [mlx-community/JOSIE-4B-Instruct-bfloat16](https://huggingface.co/mlx-community/JOSIE-4B-Instruct-bfloat16) was
converted to MLX format from [Goekdeniz-Guelmez/JOSIE-4B-Instruct](https://huggingface.co/Goekdeniz-Guelmez/JOSIE-4B-Instruct)
using mlx-lm version **0.30.6**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/JOSIE-4B-Instruct-bfloat16")

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)
```