Store › model › LLM

LFM2.5-1.2B-Instruct-GGUF

Name: LFM2.5-1.2B-Instruct-GGUF
Author: LiquidAI

by LiquidAI · source Hugging Face · updated 2026-09-22

other697 MB~2 GB RAMsource aliveunlabeled

LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

Add to LogiShell Open in the web IDE

The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:LiquidAI/LFM2.5-1.2B-Instruct-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct-GGUF
License: other (custom license: read it at the source before installing)
Requirements: about 2 GB of RAM, 697 MB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
Tags: safetensors gguf liquid lfm2.5 edge llama.cpp text-generation en ar zh fr de ja ko es endpoints_compatible

Numbers

350,989 downloads on Hugging Face
224 likes
license other
0.7 GB for LFM2.5-1.2B-Instruct-Q4_K_M.gguf
327,838 npm downloads a week for node-llama-cpp
latest node-llama-cpp@3.22.1

Numbers as of 2026-10-02 21:00 UTC, from the source API.

Summary

Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.

Reviews

No reviews yet. Reviews are written inside LogiShell: open this card in the app.

Files

file	quant	size
`LFM2.5-1.2B-Instruct-BF16.gguf`	BF16	2.2 GB
`LFM2.5-1.2B-Instruct-F16.gguf`	F16	2.2 GB
`LFM2.5-1.2B-Instruct-Q4_0.gguf`	Q4_0	664 MB
`LFM2.5-1.2B-Instruct-Q4_K_M.gguf`	Q4_K_M	697 MB
`LFM2.5-1.2B-Instruct-Q5_K_M.gguf`	Q5_K_M	804 MB
`LFM2.5-1.2B-Instruct-Q6_K.gguf`	Q6_K	918 MB
`LFM2.5-1.2B-Instruct-Q8_0.gguf`	Q8_0	1.2 GB
`LFM2.5-1.2B-Instruct-QAD-Q4_0.gguf`	Q4_0	664 MB
`qad/model.safetensors`		4.4 GB

From the source README

Try LFM • Docs • LEAP • Discord

LFM2.5-1.2B-Instruct

LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct

🏃 How to run LFM2.5

Example usage with llama.cpp:

llama-cli -hf LiquidAI/LFM2.5-1.2B-Instruct-GGUF --conversation \
    --temp 0.1 --top-k 50 --repeat-penalty 1.05

QAD Q4_0 GGUF

The Quantization-Aware Distillation (QAD) checkpoint is available as
`LFM2.5-1.2B-Instruct-QAD-Q4_0.gguf`.

This is distinct from the post-training-quantized `LFM2.5-1.2B-Instruct-Q4_0.gguf`;
both use the GGUF Q4_0 format.

Example usage with llama.cpp:

llama-cli -hf LiquidAI/LFM2.5-1.2B-Instruct-GGUF \
  --hf-file LFM2.5-1.2B-Instruct-QAD-Q4_0.gguf \
  -p "What is C. elegans?"

Card id model:hf:LiquidAI/LFM2.5-1.2B-Instruct-GGUF · collected 2026-10-02 21:00 UTC · JSON