OpenMed/LFM2-1.2B-Longevity-8bit-mlx

LFM2-1.2B-Longevity - MLX 8-bit

A native MLX conversion of LiquidAI/LFM2-1.2B-Longevity, affine-quantized to 8-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/LFM2-1.2B; OpenMed made and published this conversion. For the 4-bit sibling, see OpenMed/LFM2-1.2B-Longevity-4bit-mlx.

Family at a glance:

• PyTorch source (BF16): LiquidAI/LFM2-1.2B-Longevity - 2.18 GiB weights
• MLX 4-bit: OpenMed/LFM2-1.2B-Longevity-4bit-mlx - Apple Silicon, 0.61 GiB weights
• MLX 8-bit (this repo): OpenMed/LFM2-1.2B-Longevity-8bit-mlx - Apple Silicon, 1.16 GiB weights

Why 8-bit?

	BF16 source	This repo (Q8)
model.safetensors size	2.18 GiB	1.16 GiB (1.9x smaller)
Bits per weight, measured from the tensors	16	8.50
Parameters	1.17 B	1.17 B (unchanged)

8-bit at group size 64 is the near-lossless rung: 8 bits plus a 16-bit scale and bias per 64 weights, or 8.5 bits per weight exactly. Reach for it when memory allows and you want the closest thing to the BF16 source that still runs comfortably on Apple Silicon.

Quantization

Field	Value
Bits	8
Group size	64
Mode	affine MLX weight-only quantization
Tool	mlx_lm.convert (mlx-lm 0.31.3), -q --q-bits 8 --q-group-size 64
Quantized modules	every linear projection and the tied token embedding
Kept in BF16	RMSNorm scales and the short-convolution kernels

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/LFM2-1.2B 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

Field	Value
Source model type	lfm2 (Lfm2ForCausalLM)
Design	Hybrid Liquid model: gated short convolutions with 6 grouped-query attention layers out of 16
Hidden size	2048
Layers	16 (6 attention, 10 convolution)
Attention	32 query heads / 8 KV heads
Feed-forward width	12,288
Context length	32,768 tokens per the upstream card (max_position_embeddings 128,000)
Vocabulary	65,536, tied input/output embeddings
Language	English

File set

File	Size	Purpose
model.safetensors	1.16 GiB	MLX weights, affine-quantized
model.safetensors.index.json	22.9 KiB	Tensor index
config.json	1.7 KiB	Model config with the quantization block
modeling_lfm2.py	35.7 KiB	Reference PyTorch modeling file carried from upstream; not used by MLX
chat_template.jinja	2.5 KiB	ChatML-style chat template, unchanged from upstream
tokenizer.json	4.5 MiB	Tokenizer, unchanged from upstream
tokenizer_config.json	0.5 KiB	Tokenizer metadata, unchanged from upstream
generation_config.json	0.2 KiB	Default sampling settings, unchanged from upstream
LICENSE	10.3 KiB	LFM Open License v1.0 (upstream copy)

Weights SHA-256: 10a0b76af3ed89706863901b762c1203dd3cb200abd88127ff7a4333e6b15f49

Quick start

With mlx-lm

pip install -U mlx-lm
mlx_lm.generate --model OpenMed/LFM2-1.2B-Longevity-8bit-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/LFM2-1.2B-Longevity-8bit-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/LFM2-1.2B-Longevity-8bit-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/LFM2-1.2B-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},
}