FitMyLLM
Liquid AI/Dense

Liquid AILFM2 350M

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

chattool_use
0.35B
Parameters
125K
Context length
2
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2025-07-10
Layers
16
KV Heads
8
Head Dim
64
Family
lfm

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
1.1 GB
0.7 + 0.4 KV
good
Q5_K_S5.57
1.1 GB
0.7 + 0.4 KV
good
Q5_K_M5.7
1.1 GB
0.7 + 0.4 KV
good
Q6_K6.56
1.2 GB
0.8 + 0.4 KV
excellent
Q8_08.5
1.2 GB
0.9 + 0.4 KV
lossless
FP1616
1.6 GB
1.2 + 0.4 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run LFM2 350M now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (2)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# LFM2 350M is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=LFM2-350M+GGUF), or use the vLLM tab with the original weights.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Find the best GPU for LFM2 350M

Build Hardware for LFM2 350M
Spec sheet

LFM2 350M — 0.35B Dense.

Specifications
Parameters
0.35B
Architecture
Dense Transformer
Context Length
125K tokens
Capabilities
chat, tool_use
Release Date
2025-07-10
Provider
Liquid AI
Family
lfm
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.890.7 GB94%
Q5_K_S5.570.7 GB96%
Q5_K_M5.70.7 GB96%
Q6_K6.560.8 GB97%
Q8_08.50.9 GB100%
FP16161.2 GB100%
Benchmark scores
IFEval65.1
GPQA27.5
Compatible GPUs
30 @ Q4_K_M