LFM2.5-230M-GGUF
- Home
- / Recommended Models
- / LFM2.5-230M-GGUF
LFM2.5-230M-GGUF
VRAM needed
≈ 2 GB
Runs on phones, SBCs, and any laptop - no GPU required
AuthorLiquidAI
Parameters230M
QuantizationQ8_0
FormatGGUF
Licenselfm1.0
File size235.2 MB
Overview
Liquid's most compact LFM2.5 at high fidelity - a 230M edge model distilled from the 350M, tuned for tool use and data extraction. 213 tok/s decode on a Galaxy S25 Ultra.
Recommended hardware
≈ 2 GB VRAM to run this 230M model at the Q8_0 quantization.
Runs on phones, single-board computers (e.g. Raspberry Pi 5), and any laptop or desktop - no GPU required