What are the hardware requirements for LFM2.5 350M?

LFM2.5 350M requires approximately 0.7 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LFM2.5 350M and how large is it?

LFM2.5 350M is developed by ensu-app, a model with 350m 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 350M?

LFM2.5 350M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 350M by ensu-app — VRAM 0.7GB, 125K context

Name: LFM2.5 350M
Author: ensu-app

LFM2.5 350M is an open-source language model by ensu-app. Features: 350m LLM, VRAM: 0.7GB, Context: 125K, License: other.

Arxiv:2511.23404 Ar Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-350... Conversational De Edge En Endpoints compatible Es Eval-results Fr Ja Ko Lfm2 Lfm2.5 Liquid Pt Region:us Safetensors Zh

Model Card on HF 🤗: https://huggingface.co/ensu-app/LFM2.5-350M

LFM2.5 350M Parameters and Internals

LLM Name	LFM2.5 350M
Repository 🤗	https://huggingface.co/ensu-app/LFM2.5-350M
Base Model(s)	LiquidAI/LFM2.5-350M-Base LiquidAI/LFM2.5-350M-Base
Model Size	350m
Required VRAM	0.7 GB
Updated	2026-10-17
Maintainer	ensu-app
Model Type	lfm2
Model Files	0.7 GB
Supported Languages	en ar zh fr de ja ko es pt
Model Architecture	Lfm2ForCausalLM
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	5.0.0rc1
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	65536

Rank the LFM2.5 350M 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

Best Alternatives to LFM2.5 350M

Best Alternatives	Context / RAM	Downloads	Likes
Minico M1 Preview	125K / 0.8 GB	473	1
LFM2.5 350M	125K / 0.7 GB	91807	384
LFM2.5 350M Thinking 0003	125K / 0.7 GB	1022	0
LFM2.5 350M IT Extract	125K / 0.7 GB	660	0
LFM2.5 350M Base	125K / 0.7 GB	9543	24
LFM2.5 350M Thinking	125K / 0.7 GB	604	0
LFM2.5 350M RLCD	125K / 0.7 GB	204	3
LFM2 350M Extract Facts	125K / 0.7 GB	40	0
LFM2.5 350M Ifstruct	125K / 0.7 GB	33	1
LFM2.5 350M Memory Extractor	125K / 0.7 GB	144	1

Note: green Score (e.g. "73.2") means that the model is better than ensu-app/LFM2.5-350M.