What are the hardware requirements for LFM2 350M?

LFM2 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 350M and how large is it?

LFM2 350M is developed by LiquidAI, 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 350M?

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

LFM2 350M by LiquidAI — VRAM 0.7GB, 125K context

Name: LFM2 350M
Rating: 1 (1 reviews)
Author: LiquidAI

LFM2 350M is an open-source language model by LiquidAI. Features: 350m LLM, VRAM: 0.7GB, Context: 125K, License: other, LLM Explorer Score: 0.27.

Arxiv:2511.23404 Ar Conversational De Deploy:azure Edge En Endpoints compatible Es Fr Ja Ko Lfm2 Liquid Region:us Safetensors Zh

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2-350M

LFM2 350M Benchmarks

LLME Score: 0.27135

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

LFM2 350M Parameters and Internals

LLM Name	LFM2 350M
Repository 🤗	https://huggingface.co/LiquidAI/LFM2-350M
Model Size	350m
Required VRAM	0.7 GB
Updated	2026-07-13
Maintainer	LiquidAI
Model Type	lfm2
Model Files	0.7 GB
Supported Languages	en ar zh fr de ja ko es
Model Architecture	Lfm2ForCausalLM
License	other
Context Length	128000
Model Max Length	128000
Transformers Version	4.54.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
Vocabulary Size	65536
Torch Data Type	bfloat16

Quantized Models of the LFM2 350M

Model	Likes	Downloads
CHEETAH 350M Merged FP16	0	13
LFM2 350M 8bit	4	423
LFM2 350M 4bit	4	132
Kulyk En Uk	5	34

Best Alternatives to LFM2 350M

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 350M	125K / 0.7 GB	93737	376
LFM2.5 350M Base	125K / 0.7 GB	29104	20
Gallium 350M	125K / 0.7 GB	273	9
LiquidAI LFM2.5 350M SYNTH	125K / 0.7 GB	222	1
LFM2.5 350M ONNX	125K / GB	759	4
LFM2 350M CPT	125K / 0.7 GB	632	0
Chiboard 1 S1	125K / 0.7 GB	20	0
LFM2.5 350M SFT Fable5 Glint	125K / 0.7 GB	40	0
....5 350M Home Assistant Sft V13	125K / 0.7 GB	100	0
....5 350M Tool Calling Merged V2	125K / 0.7 GB	63	0

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

Rank the LFM2 350M Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 55396 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, Arena and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

LFM2 350M by LiquidAI