Store › model › LLM

LFM2.5-2.6B-GGUF

Name: LFM2.5-2.6B-GGUF
Author: LiquidAI

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

other1.6 GB~3 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/LFM2.5-2.6B-GGUF and its progress lives in the Resource Center.

Source and license

Source: https://huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF
License: other (custom license: read it at the source before installing)
Requirements: about 3 GB of RAM, 1.6 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
Tags: gguf safetensors liquid lfm2.5 llama.cpp text-generation ar zh en fr de hi id it ja ko

Numbers

1,066,051 downloads on Hugging Face
360 likes
license other
1.6 GB for LFM2.5-2.6B-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 20:59 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
`LFM2.5-2.6B-BF16.gguf`	BF16	5.0 GB
`LFM2.5-2.6B-F16.gguf`	F16	5.0 GB
`LFM2.5-2.6B-Q4_0.gguf`	Q4_0	1.5 GB
`LFM2.5-2.6B-Q4_K_M.gguf`	Q4_K_M	1.6 GB
`LFM2.5-2.6B-Q5_K_M.gguf`	Q5_K_M	1.8 GB
`LFM2.5-2.6B-Q6_K.gguf`	Q6_K	2.1 GB
`LFM2.5-2.6B-Q8_0.gguf`	Q8_0	2.7 GB
`LFM2.5-2.6B-QAD-Q4_0.gguf`	Q4_0	1.5 GB
`qad/model.safetensors`		10 GB

From the source README

Try LFM •
Docs •
LEAP •
Discord

LFM2.5-2.6B-GGUF

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/LFM2.5-2.6B

🏃 How to run LFM2

Example usage with llama.cpp:

llama-cli -hf LiquidAI/LFM2.5-2.6B-GGUF --conversation \
    --temp 0.1 --top-k 50 --repeat-penalty 1.1

QAD Q4_0 GGUF

The Quantization-Aware Distillation (QAD) checkpoint is available as
`LFM2.5-2.6B-QAD-Q4_0.gguf`.

This is distinct from the post-training-quantized `LFM2.5-2.6B-Q4_0.gguf`;
both use the GGUF Q4_0 format.

QAD source weights (safetensors)

The original FP32 QAD source checkpoint is available in
`qad/`, with its model config,
tokenizer, generation defaults, and the same chat template as the released QAD GGUF.
It can be loaded in Transformers by passing `subfolder="qad"`:

Card id model:hf:LiquidAI/LFM2.5-2.6B-GGUF · collected 2026-10-02 20:59 UTC · JSON