LFM2-2.6B-Longevity-4bit-mlx

LFM2-2.6B-Longevity - MLX 4-bit

A native MLX conversion of LiquidAI/LFM2-2.6B-Longevity, affine-quantized to 4-bit (group size 64) with mlx_lm for on-device use on Apple Silicon. The model is Liquid AI and Insilico Medicine's Longevity-LLM fine-tune of LiquidAI/LFM2-2.6B; OpenMed made and published this conversion. For the 8-bit sibling, see OpenMed/LFM2-2.6B-Longevity-8bit-mlx.

Family at a glance:

• PyTorch source (BF16): LiquidAI/LFM2-2.6B-Longevity - 4.79 GiB weights
• MLX 4-bit (this repo): OpenMed/LFM2-2.6B-Longevity-4bit-mlx - Apple Silicon, 1.35 GiB weights
• MLX 8-bit: OpenMed/LFM2-2.6B-Longevity-8bit-mlx - Apple Silicon, 2.54 GiB weights

Why 4-bit?

4-bit is the rung to reach for when memory is the constraint - a phone or a base-model Mac - and the weights above are the whole download.

Quantization

The tokenizer, chat template and generation defaults are the upstream files, unchanged.

What it does

Longevity-LLM (L-LLM) is a family of compact, domain-adapted language models for interpreting heterogeneous aging-biology data - genomic, proteomic and clinical - developed jointly by Insilico Medicine and Liquid AI. This checkpoint was produced by full-parameter supervised fine-tuning of LiquidAI/LFM2-2.6B on aging-related multi-omics and clinical data, and accompanies the study An Open Benchmark and Language Models for AI in Aging Biology (Zhavoronkov et al., 2026). See the upstream model card for the training corpus and evaluation.

Prompts use a ChatML-style template with a dynamic-thinking switch: suffix a user turn with /think for a reasoning trace or /no_think for a direct answer. The template is bundled, so apply_chat_template and mlx_lm handle it for you.

Architecture

File set

Weights SHA-256: c5f4432baaa4a0e8c3be2fb31c68af3b65e97cf9f2ce32b095f3b40791674c87

Quick start

With mlx-lm

pip install -U mlx-lm
mlx_lm.generate --model OpenMed/LFM2-2.6B-Longevity-4bit-mlx \
  --prompt "Which biomarkers in a routine blood panel are most informative about biological age, and why? /no_think" \
  --max-tokens 400

from mlx_lm import load, generate

model, tokenizer = load("OpenMed/LFM2-2.6B-Longevity-4bit-mlx")

messages = [
    {"role": "system", "content": "You are a biomedical AI specialized in aging biology, trained on genomic, proteomic, and clinical data."},
    {"role": "user", "content": "A 58-year-old has HbA1c 6.1%, hs-CRP 3.4 mg/L and an epigenetic age 6 years above chronological age. What do these point to, and what would you want measured next? /no_think"},
]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
print(generate(model, tokenizer, prompt=prompt, max_tokens=500))

With LM Studio

Download the repository into your LM Studio models directory (or search for OpenMed/LFM2-2.6B-Longevity-4bit-mlx in the app); the MLX engine loads it directly.

Outputs are model predictions for research use, not clinical advice.

Provenance and license

This repository is a quantized derivative of LiquidAI/LFM2-2.6B-Longevity. model.safetensors was produced by mlx_lm.convert from the upstream BF16 weights and config.json carries the added quantization block; every other file is an unchanged upstream copy. It is distributed under the upstream LFM Open License v1.0: free for research and for commercial use by entities below the license's revenue threshold (US$10M annual revenue), and not licensed for commercial use above it - read the LICENSE before shipping. Copyright in the model remains with Liquid AI, Inc. and Insilico Medicine; OpenMed claims none.

Citation

Please cite the upstream work:

@article{zhavoronkov2026longevitybench,
  title   = {An Open Benchmark and Language Models for AI in Aging Biology},
  author  = {Zhavoronkov, Alex and Naumov, Vladimir and Sidorenko, Denis and Aliper, Alex and Aladinskiy, Vladimir and Hasani, Ramin and Amini, Alexander and Nasto, Katerina and Reymond, Mathieu and Shayakhmetov, Rim and Miftakhutdinov, Zulfat and Gladyshev, Vadim N. and Galkin, Fedor},
  journal = {Cell},
  volume  = {189},
  pages   = {5980--5994},
  year    = {2026},
  doi     = {10.1016/j.cell.2026.08.026},
  url     = {https://www.cell.com/cell/fulltext/S0092-8674(26)00999-2},
}