What are the hardware requirements for LFM2.5 VL 1.6B Extract?

LFM2.5 VL 1.6B Extract requires approximately 3.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LFM2.5 VL 1.6B Extract and how large is it?

LFM2.5 VL 1.6B Extract is developed by LiquidAI, a model with 1.6b 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 VL 1.6B Extract?

LFM2.5 VL 1.6B Extract is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 VL 1.6B Extract by LiquidAI — VRAM 3.2GB

Name: LFM2.5 VL 1.6B Extract
Author: LiquidAI

LFM2.5 VL 1.6B Extract is an open-source language model by LiquidAI. Features: 1.6b LLM, VRAM: 3.2GB, License: other, LLM Explorer Score: 0.29.

Arxiv:2502.14786 Arxiv:2511.23404 Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-vl-... Conversational Edge En Endpoints compatible Image-text-to-text Lfm2 Lfm2.5 Lfm2 vl Liquid Region:us Safetensors Vision

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B-Extract

LFM2.5 VL 1.6B Extract Parameters and Internals

LLM Name	LFM2.5 VL 1.6B Extract
Repository 🤗	https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B-Extract
Base Model(s)	LiquidAI/LFM2.5-VL-1.6B LiquidAI/LFM2.5-VL-1.6B
Model Size	1.6b
Required VRAM	3.2 GB
Updated	2026-08-09
Maintainer	LiquidAI
Model Type	lfm2_vl
Model Files	3.2 GB
Supported Languages	en
Model Architecture	Lfm2VlForConditionalGeneration
License	other
Transformers Version	5.9.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>

Rank the LFM2.5 VL 1.6B Extract 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 VL 1.6B Extract

Best Alternatives	Context / RAM	Downloads	Likes
LFM2 VL 1.6B	0K / 3.2 GB	18236	233
LFM2.5 VL 1.6B ONNX	0K / GB	430	33
LFM2 VL 1.6B Bf16	0K / 3.2 GB	21	1
LFM2 VL 1.6B 4bit	0K / 1.5 GB	4877	1
LFM2 VL 1.6B 8bit	0K / 2.1 GB	50	10
LFM2 VL 1.6B 5bit	0K / 1.6 GB	28	1
LFM2 VL 1.6B 6bit	0K / 1.8 GB	18	1