LiquidAI / LFM2.5-350M-MLX-8bit

huggingface.co
Total runs: 1.7K
24-hour runs: 0
7-day runs: -352
30-day runs: -478
Model's Last Updated: April 02 2026
text-generation

Introduction of LFM2.5-350M-MLX-8bit

Model Details of LFM2.5-350M-MLX-8bit


LFM2.5-350M-MLX-8bit

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 8-bit
Group Size 64
Size 381 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-8bit")

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 .

Runs of LiquidAI LFM2.5-350M-MLX-8bit on huggingface.co

1.7K
Total runs
0
24-hour runs
0
3-day runs
-352
7-day runs
-478
30-day runs

More Information About LFM2.5-350M-MLX-8bit huggingface.co Model

More LFM2.5-350M-MLX-8bit license Visit here:

https://choosealicense.com/licenses/lfm1.0

LFM2.5-350M-MLX-8bit huggingface.co

LFM2.5-350M-MLX-8bit huggingface.co is an AI model on huggingface.co that provides LFM2.5-350M-MLX-8bit's model effect (), which can be used instantly with this LiquidAI LFM2.5-350M-MLX-8bit model. huggingface.co supports a free trial of the LFM2.5-350M-MLX-8bit model, and also provides paid use of the LFM2.5-350M-MLX-8bit. Support call LFM2.5-350M-MLX-8bit model through api, including Node.js, Python, http.

LFM2.5-350M-MLX-8bit huggingface.co Url

https://huggingface.co/LiquidAI/LFM2.5-350M-MLX-8bit

LiquidAI LFM2.5-350M-MLX-8bit online free

LFM2.5-350M-MLX-8bit huggingface.co is an online trial and call api platform, which integrates LFM2.5-350M-MLX-8bit's modeling effects, including api services, and provides a free online trial of LFM2.5-350M-MLX-8bit, you can try LFM2.5-350M-MLX-8bit online for free by clicking the link below.

LiquidAI LFM2.5-350M-MLX-8bit online free url in huggingface.co:

https://huggingface.co/LiquidAI/LFM2.5-350M-MLX-8bit

LFM2.5-350M-MLX-8bit install

LFM2.5-350M-MLX-8bit is an open source model from GitHub that offers a free installation service, and any user can find LFM2.5-350M-MLX-8bit on GitHub to install. At the same time, huggingface.co provides the effect of LFM2.5-350M-MLX-8bit install, users can directly use LFM2.5-350M-MLX-8bit installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

LFM2.5-350M-MLX-8bit install url in huggingface.co:

https://huggingface.co/LiquidAI/LFM2.5-350M-MLX-8bit

Url of LFM2.5-350M-MLX-8bit

LFM2.5-350M-MLX-8bit huggingface.co Url

Provider of LFM2.5-350M-MLX-8bit huggingface.co

LiquidAI
ORGANIZATIONS

Other API from LiquidAI

huggingface.co

Total runs: 119.0K
Run Growth: 76.2K
Growth Rate: 64.05%
Updated:April 02 2026
huggingface.co

Total runs: 104.2K
Run Growth: 78.6K
Growth Rate: 75.40%
Updated:March 30 2026
huggingface.co

Total runs: 100.4K
Run Growth: 58.9K
Growth Rate: 58.70%
Updated:February 13 2026
huggingface.co

Total runs: 94.9K
Run Growth: 25.8K
Growth Rate: 27.18%
Updated:March 30 2026
huggingface.co

Total runs: 20.2K
Run Growth: -12.8K
Growth Rate: -63.43%
Updated:March 30 2026
huggingface.co

Total runs: 15.0K
Run Growth: -24.0K
Growth Rate: -159.48%
Updated:March 30 2026
huggingface.co

Total runs: 11.9K
Run Growth: -170
Growth Rate: -1.43%
Updated:March 30 2026
huggingface.co

Total runs: 9.6K
Run Growth: -1.9K
Growth Rate: -19.52%
Updated:March 30 2026
huggingface.co

Total runs: 6.5K
Run Growth: 449
Growth Rate: 6.86%
Updated:March 30 2026
huggingface.co

Total runs: 3.8K
Run Growth: -692
Growth Rate: -18.35%
Updated:March 30 2026