What are the hardware requirements for LFM2.5 VL 3B MLX Bf16?

LFM2.5 VL 3B MLX Bf16 requires approximately 6.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LFM2.5 VL 3B MLX Bf16 and how large is it?

LFM2.5 VL 3B MLX Bf16 is developed by LiquidAI, a model with 3b 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 3B MLX Bf16?

LFM2.5 VL 3B MLX Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2.5 VL 3B MLX Bf16 by LiquidAI — VRAM 6.2GB

Name: LFM2.5 VL 3B MLX Bf16
Author: LiquidAI

LFM2.5 VL 3B MLX Bf16 is an open-source language model by LiquidAI. Features: 3b LLM, VRAM: 6.2GB, License: other, LLM Explorer Score: 0.34.

Ar Base model:liquidai/lfm2.5-vl-... Base model:quantized:liquidai/... Conversational Custom code De Edge En Es Fr Hi Id Image-text-to-text It Ja Ko Lfm2 Lfm2-vl Lfm2.5 Lfm2.5-vl Lfm2 vl Liquid Mlx Mlx vlm Pl Pt Region:us Ru Safetensors Sharded Tensorflow Th Vi Zh

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-VL-3B-MLX-bf16

LFM2.5 VL 3B MLX Bf16 Parameters and Internals

LLM Name	LFM2.5 VL 3B MLX Bf16
Repository 🤗	https://huggingface.co/LiquidAI/LFM2.5-VL-3B-MLX-bf16
Base Model(s)	LiquidAI/LFM2.5-VL-3B LiquidAI/LFM2.5-VL-3B
Model Size	3b
Required VRAM	6.2 GB
Updated	2026-08-14
Maintainer	LiquidAI
Model Type	lfm2_vl
Model Files	5.3 GB: 1-of-2 0.9 GB: 2-of-2
Supported Languages	ar zh en fr de hi id it ja ko pl pt ru es th vi
Model Architecture	Lfm2VlForConditionalGeneration
License	other
Transformers Version	5.8.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>

Rank the LFM2.5 VL 3B MLX Bf16 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 3B MLX Bf16

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 VL 3B	0K / 6.2 GB	0	73
LFM2.5 VL 3B	0K / 6.2 GB	259	2
LFM2.5 VL 3B ONNX	0K / GB	10	14
LFM2 VL 3B	0K / 6 GB	12342	140
LFM2.5 VL 3B Heretic	0K / 6.2 GB	0	1
LFM2.5 VL 3B MLX 4bit	0K / 2.4 GB	272	15
LFM2.5 VL 3B MLX 8bit	0K / 3.7 GB	324	13
LFM2.5 VL 3B MLX 6bit	0K / 3 GB	83	12
LFM2.5 VL 3B MLX 5bit	0K / 2.7 GB	59	12
LFM2 VL 3B 4bit	0K / 2.3 GB	296	4

Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2.5-VL-3B-MLX-bf16.