LFM2.5-350M-MLX-4bit

LiquidAI/LFM2.5-350M-MLX-4bit

LFM2.5-350M-MLX-4bit is a text generation model from LiquidAI. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as other.

<div align="center" <img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="width: 100%; max-width: 100%; height: auto; display: inlin…

Downloads · 30 days

740

14% of all-time downloads

All-time downloads

5.1K

Public

Parameters

354M

222 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors222 MB · 98%

Parameter types

How the weights are stored.

U32354M · 100%

Try a prompt

Base models

LiquidAI/LFM2.5-350M

Model card

From the Hugging Face model README

<div align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;" /> <div style="display: flex; justify-content: center; gap: 0.5em; margin-bottom: 1em;"> <a href="https://playground.liquid.ai/"><strong>Try LFM</strong></a> • <a href="https://docs.liquid.ai/lfm/getting-started/welcome"><strong>Docs</strong></a> • <a href="https://leap.liquid.ai/"><strong>LEAP</strong></a> • <a href="https://discord.com/invite/liquid-ai"><strong>Discord</strong></a> </div> </div> <br>

LFM2.5-350M-MLX-4bit

MLX export of LFM2.5-350M for Apple Silicon inference.

LFM2.5-350M is a compact multilingual base model built on LiquidAI's hybrid architecture, combining convolutional and attention layers for efficient long-context processing.

Model Details

Property	Value
Parameters	350M
Precision	4-bit
Group Size	64
Size	212 MB
Context Length	128K

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate
from mlx_lm.sample_utils import make_sampler

model, tokenizer = load("LiquidAI/LFM2.5-350M-MLX-4bit")

response = generate(
    model,
    tokenizer,
    prompt="The capital of France is",
    max_tokens=100,
    sampler=make_sampler(temp=0.7),
    verbose=True,
)

Other Precisions

License

This model is released under the LFM 1.0 License.

Task: Text Generation
Library: mlx
Type: lfm2
License: other
Languages: en, ar, zh, fr, de, ja
Created: Mar 25, 2026
Updated: Aug 12, 2026