metadata
library_name: mlx
license: other
license_name: lfm1.0
license_link: LICENSE
language:
- en
- ja
- ko
- fr
- es
- de
- it
- pt
- ar
- zh
pipeline_tag: image-text-to-text
tags:
- liquid
- lfm2.5-vl
- lfm2.5
- edge
- mlx
base_model: LiquidAI/LFM2.5-VL-450M
Try LFM • Documentation • LEAP • Blog
LFM2.5-VL-450M-MLX-5bit
MLX export of LFM2.5-VL-450M for Apple Silicon inference.
LFM2.5-VL-450M is a vision-language model built on the LFM2.5-350M backbone with a SigLIP2 NaFlex vision encoder (86M). It supports OCR, document comprehension, multilingual vision understanding, bounding box prediction, and function calling.
Model Details
| Property | Value |
|---|---|
| Parameters | 450M |
| Precision | 5-bit |
| Group Size | 64 |
| Size | 0.39 GB |
| Context Length | 32K |
| Vision Encoder | SigLIP2 NaFlex (86M) |
| Native Resolution | up to 512x512 |
Quickstart
uv pip install 'mlx-vlm==0.3.9'
from mlx_vlm import load, generate
from mlx_vlm.utils import load_image
model, processor = load("LiquidAI/LFM2.5-VL-450M-MLX-5bit")
image = load_image("photo.jpg")
# Apply chat template (required for LFM2.5-VL)
messages = [{"role": "user", "content": [
{"type": "image"},
{"type": "text", "text": "What do you see in this image?"},
]}]
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
result = generate(
model,
processor,
prompt,
[image],
temp=0.1,
min_p=0.15,
repetition_penalty=1.05,
verbose=True,
)
print(result.text)
Recommended Sampling Parameters
| Parameter | Value |
|---|---|
| temperature | 0.1 |
| min_p | 0.15 |
| repetition_penalty | 1.05 |
License
This model is released under the LFM 1.0 License.