LFM3-Omni-2B-Abliterated-Arete-ONNX-WebGPU

by balllvin

Task
Vision-language (image + text to text)
Category
Image
License
Custom (other)
Commercial use
Check the license
The license isn't a standard one; read the model card on Hugging Face before using it commercially.
Size
About 2 billion parameters
Memory to load
~2 GB (estimate)
Format
MLX
Runs on
CPU
Access
Gated: accept the publisher's terms on Hugging Face
Downloads (last 30 days)
0
Likes
0
Last updated
November 16, 2026

How to run it

This is an MLX build for Apple silicon Macs; run it with Apple's MLX framework (mlx-lm for language models).

Plan for roughly 2 GB of memory to load it (our estimate from its size and format).

Downloads are gated: accept the publisher's terms on Hugging Face first.

The model card on Hugging Face has the exact usage code.

Where to run it

In the cloud

Needs about 2 GB: a 24 GB GPU such as an RTX 4090 or RTX A5000 is enough.

  • RunPod · rent a GPU by the hour (affiliate link)

Related vision-language (image + text to text) models

Data from Hugging Face's public API, last checked November 16, 2026. Downloads are Hugging Face's count for the last 30 days.