---
title: tiny-aya-fire-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/tiny-aya-fire-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/tiny-aya-fire-4bit.md"
repository: mlx-community/tiny-aya-fire-4bit
last_updated: 2026-03-06
license: cc-by-nc-4.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - cohere2
architectures:
  - Cohere2ForCausalLM
base_model:
  - CohereLabs/tiny-aya-fire
base_model_relation: quantized
parameters: 523.4M
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - nl
  - fr
  - it
  - pt
  - ro
  - es
  - cs
  - pl
  - uk
  - ru
  - el
  - de
  - da
  - sv
  - no
  - ca
  - gl
  - cy
  - ga
  - eu
  - hr
  - lv
  - lt
  - sk
  - sl
  - et
  - fi
  - hu
  - sr
  - bg
  - ar
  - fa
  - ur
  - tr
  - mt
  - he
  - hi
  - mr
  - bn
  - gu
  - pa
  - ta
  - te
  - ne
  - tl
  - ms
  - id
  - vi
  - jv
  - km
  - th
  - lo
  - zh
  - my
  - ja
  - ko
  - am
  - ha
  - ig
  - mg
  - sn
  - sw
  - wo
  - xh
  - yo
  - zu
inference_backends:
  - "deploy_task text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 8
stars: 0
tags:
  - mlx
---

# tiny-aya-fire-4bit

> tiny-aya-fire-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/tiny-aya-fire-4bit

mlx-community/tiny-aya-fire-4bit 是 ModelScope 魔搭社区上的 523.4M 参数text-generation模型，采用 cc-by-nc-4.0 许可，基于 CohereLabs/tiny-aya-fire 构建，可用 deploy_task text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/tiny-aya-fire-4bit
- **License**: cc-by-nc-4.0
- **Tasks**: text-generation
- **Parameters**: 523.4M
- **Base model**: CohereLabs/tiny-aya-fire
- **Inference backends**: deploy_task text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 8
- **Stars**: 0
- **Last updated**: 2026-03-06

Source: https://www.modelscope.cn/models/mlx-community/tiny-aya-fire-4bit

---

# mlx-community/tiny-aya-fire-4bit

This model [mlx-community/tiny-aya-fire-4bit](https://huggingface.co/mlx-community/tiny-aya-fire-4bit) was
converted to MLX format from [CohereLabs/tiny-aya-fire](https://huggingface.co/CohereLabs/tiny-aya-fire)
using mlx-lm version **0.30.7**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/tiny-aya-fire-4bit")

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)
```