What are the hardware requirements for LFM2.5 VL 450M MLX 5bit?

LFM2.5 VL 450M MLX 5bit requires approximately 0.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LFM2.5 VL 450M MLX 5bit and how large is it?

LFM2.5 VL 450M MLX 5bit is developed by LiquidAI, a model with 450m 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 450M MLX 5bit?

LFM2.5 VL 450M MLX 5bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 VL 450M MLX 5bit by LiquidAI — VRAM 0.4GB

Name: LFM2.5 VL 450M MLX 5bit
Author: LiquidAI

LFM2.5 VL 450M MLX 5bit is an open-source language model by LiquidAI. Features: 450m LLM, VRAM: 0.4GB, License: other, Quantized, LLM Explorer Score: 0.24.

5-bit 5bit Ar Base model:liquidai/lfm2.5-vl-... Base model:quantized:liquidai/... Conversational De Edge En Es Fr Image-text-to-text It Ja Ko Lfm2-vl Lfm2.5 Lfm2.5-vl Liquid Mlx Pt Quantized Region:us Safetensors Zh

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-VL-450M-MLX-5bit

LFM2.5 VL 450M MLX 5bit Parameters and Internals

LLM Name	LFM2.5 VL 450M MLX 5bit
Repository 🤗	https://huggingface.co/LiquidAI/LFM2.5-VL-450M-MLX-5bit
Base Model(s)	LiquidAI/LFM2.5-VL-450M LiquidAI/LFM2.5-VL-450M
Model Size	450m
Required VRAM	0.4 GB
Updated	2026-08-08
Maintainer	LiquidAI
Model Type	lfm2-vl
Model Files	0.4 GB
Supported Languages	en ja ko fr es de it pt ar zh
Quantization Type	5bit
Model Architecture	Lfm2VlForConditionalGeneration
License	other
Transformers Version	5.0.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>

Rank the LFM2.5 VL 450M MLX 5bit 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 450M MLX 5bit

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 VL 450M MLX 4bit	0K / 0.4 GB	315	9
LFM2 VL 450M 8bit	0K / 0.6 GB	238	11
LFM2 VL 450M 4bit	0K / 0.4 GB	237	1
LFM2 VL 450M 5bit	0K / 0.4 GB	19	1
LFM2.5 VL 450M ONNX	0K / GB	1174	32
LFM2 VL 450M Bf16	0K / 0.9 GB	24	1

Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2.5-VL-450M-MLX-5bit.