---
title: Falcon-H1-1.5B-Instruct-6bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Falcon-H1-1.5B-Instruct-6bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Falcon-H1-1.5B-Instruct-6bit.md"
repository: mlx-community/Falcon-H1-1.5B-Instruct-6bit
last_updated: 2025-09-27
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - falcon_h1
architectures:
  - FalconH1ForCausalLM
base_model:
  - tiiuae/Falcon-H1-1.5B-Instruct
base_model_relation: quantized
parameters: 340.6M
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ar
  - cs
  - de
  - en
  - es
  - fr
  - hi
  - it
  - ja
  - ko
  - nl
  - pl
  - pt
  - ro
  - ru
  - sv
  - ur
  - zh
inference_backends:
  - "deploy_task text/emb"
  - "vllm 0.9.2"
downloads: 243
stars: 0
tags:
  - falcon-h1
  - mlx
---

# Falcon-H1-1.5B-Instruct-6bit

> Falcon-H1-1.5B-Instruct-6bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Falcon-H1-1.5B-Instruct-6bit

mlx-community/Falcon-H1-1.5B-Instruct-6bit 是 ModelScope 魔搭社区上的 340.6M 参数text-generation模型，采用 other 许可，基于 tiiuae/Falcon-H1-1.5B-Instruct 构建，可用 deploy_task text/emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/Falcon-H1-1.5B-Instruct-6bit
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 340.6M
- **Base model**: tiiuae/Falcon-H1-1.5B-Instruct
- **Inference backends**: deploy_task text/emb, vllm 0.9.2
- **Tags**: falcon-h1, mlx
- **Downloads**: 243
- **Stars**: 0
- **Last updated**: 2025-09-27

Source: https://www.modelscope.cn/models/mlx-community/Falcon-H1-1.5B-Instruct-6bit

---

# mlx-community/Falcon-H1-1.5B-Instruct-6bit

This model [mlx-community/Falcon-H1-1.5B-Instruct-6bit](https://huggingface.co/mlx-community/Falcon-H1-1.5B-Instruct-6bit) was
converted to MLX format from [tiiuae/Falcon-H1-1.5B-Instruct](https://huggingface.co/tiiuae/Falcon-H1-1.5B-Instruct)
using mlx-lm version **0.28.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Falcon-H1-1.5B-Instruct-6bit")

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)
```