What are the hardware requirements for LFM2.5 2.6B?

LFM2.5 2.6B requires approximately 5.4 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LFM2.5 2.6B and how large is it?

LFM2.5 2.6B is developed by LiquidAI, a model with 2.6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate LFM2.5 2.6B?

LFM2.5 2.6B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 2.6B by LiquidAI — VRAM 5.4GB, 128K context

Name: LFM2.5 2.6B
Author: LiquidAI

LFM2.5 2.6B is an open-source language model by LiquidAI. Features: 2.6b LLM, VRAM: 5.4GB, Context: 128K, License: other, LLM Explorer Score: 0.44.

Arxiv:2511.23404 Ar Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-2.6... Conversational De Edge En Endpoints compatible Es Eval-results Fr Hi Id It Ja Ko Lfm2 Lfm2.5 Liquid Pl Pt Region:us Ru Safetensors Sharded Tensorflow Th Vi Zh

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-2.6B

LFM2.5 2.6B Parameters and Internals

LLM Name	LFM2.5 2.6B
Repository 🤗	https://huggingface.co/LiquidAI/LFM2.5-2.6B
Base Model(s)	LiquidAI/LFM2.5-2.6B-Base LiquidAI/LFM2.5-2.6B-Base
Model Size	2.6b
Required VRAM	5.4 GB
Updated	2026-08-08
Maintainer	LiquidAI
Model Type	lfm2
Model Files	5.3 GB: 1-of-2 0.1 GB: 2-of-2
Supported Languages	ar zh en fr de hi id it ja ko pl pt ru es th vi
Model Architecture	Lfm2ForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	128000

Rank the LFM2.5 2.6B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the LFM2.5 2.6B

Model	Likes	Downloads	VRAM
...ABLITERATED PHILADELPHIA CLASS	5	2203	5 GB
LFM2.5 2.6B 4bit	3	1509	1 GB
LFM2.5 2.6B 8bit	3	854	2 GB
LFM2.5 2.6B OptiQ 4bit	2	337	2 GB
LFM 2.5 Coder 2.6B	1	224	5 GB
...2.5 2.6B Thinkingcap Distiller	2	172	1 GB
LMF 2.5 2B Code Lora	2	30	0 GB
LFM2.5 2.6B MLX 8bit	1	60	2 GB
LFM2.5 2.6B MLX 6bit	1	52	2 GB
LFM2.5 2.6B MLX 5bit	1	49	1 GB

Best Alternatives to LFM2.5 2.6B

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 2.6B RLCD	128K / 5.4 GB	352	6
Cyber Prime 1 2.6B	128K / 5.4 GB	735	22
Transductor High V3	128K / 5.4 GB	1199	0
...fm2.5 2.6B Fable5 Coding Agent	128K / 5.4 GB	520	11
LFM 2.5 2.6B Heretic	128K / 5.4 GB	486	5
LFM2.5 2.6B Abliterated	128K / 5.4 GB	196	0
Lfm2.5 2.6B Manumit V1	128K / 5.4 GB	354	0
...M2.5 2.6B Abliterated Advanced	128K / 5.4 GB	255	1
...max Video Prompt Enhancer 2.6B	128K / 5.4 GB	229	1
...P Mini 2.6B Instruct 2608 V0.1	128K / 5.4 GB	158	1