LiquidAI/LFM2.5-8B-A1B-MLX-8bit

This model LiquidAI/LFM2.5-8B-A1B-MLX-8bit was converted to MLX format from LiquidAI/LFM2.5-8B-A1B using mlx-lm version 0.31.3.

About this quantization

Quantized to 8 bits per weight (group size 64, affine mode). MoE routing gates retained at 8 bits.

For base model details, capabilities, and recommended generation settings, see the original model card.

Use with mlx

pip install mlx-lm

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

model, tokenizer = load("LiquidAI/LFM2.5-8B-A1B-MLX-8bit")

prompt = "What is C. elegans?"

if tokenizer.chat_template is not None:
 messages = [{"role": "user", "content": prompt}]
 prompt = tokenizer.apply_chat_template(
 messages, add_generation_prompt=True
 )

sampler = make_sampler(temp=0.2, top_k=80)
logits_processors = make_logits_processors(repetition_penalty=1.05)

response = generate(
 model, tokenizer, prompt=prompt,
 sampler=sampler, logits_processors=logits_processors,
 verbose=True,
)

Chat Template

LFM2.5 uses a ChatML-like format. See the Chat Template documentation for details. Example:

<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
What is C. elegans?<|im_end|>
<|im_start|>assistant

Because LFM2.5-8B-A1B is a reasoning model, assistant turns contain an explicit chain of thought before the final answer. tokenizer.apply_chat_template() formats messages automatically.

Tool Use

LFM2.5 supports function calling. Pass tools to tokenizer.apply_chat_template(..., tools=...). See the Tool Use documentation for the full guide.

License

LFM Open License v1.0 — see the LICENSE file or the original model card for terms.

Citation

@article{liquidAI20268BA1B,
 author = {Liquid AI},
 title = {LFM2.5-8B-A1B: Personal Assistant On Your Laptop},
 journal = {Liquid AI Blog},
 year = {2026},
 note = {www.liquid.ai/blog/lfm2-5-8b-a1b},
}

@article{liquidai2025lfm2,
 title = {LFM2 Technical Report},
 author = {Liquid AI},
 journal = {arXiv preprint arXiv:2511.23404},
 year = {2025}
}

Base model