LLM EXPLORER 58,425 MODELS INDEXED

LFM2.5 VL 1.6B 8bit by mlx-community

By mlx-community · 97 downloads
HF Repo ↗ Copy URL

LFM2.5 VL 1.6B 8bit is an open-source language model by mlx-community. Features: 1.2b LLM, VRAM: 2.1GB, License: other, Quantized, LLM Explorer Score: 0.22.

  8-bit   8bit   Ar Base model:liquidai/lfm2.5-1.2... Base model:quantized:liquidai/...   Conversational   De   Edge   En   Endpoints compatible   Es   Fr   Image-text-to-text   Ja   Ko   Lfm2   Lfm2-vl   Lfm2.5   Lfm2.5-vl   Lfm2 vl   Liquid   Mlx   Quantized   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/LFM2.5-VL-1.6B-8bit 

LFM2.5 VL 1.6B 8bit Parameters and Internals

LLM NameLFM2.5 VL 1.6B 8bit
Repository 🤗https://huggingface.co/mlx-community/LFM2.5-VL-1.6B-8bit 
Base Model(s)  LiquidAI/LFM2.5-1.2B-Base   LiquidAI/LFM2.5-1.2B-Base
Model Size1.2b
Required VRAM2.1 GB
Updated2026-08-08
Maintainermlx-community
Model Typelfm2_vl
Model Files  2.1 GB
Supported Languagesen ja ko fr es de ar zh
Quantization Type8bit
Model ArchitectureLfm2VlForConditionalGeneration
Licenseother
Transformers Version5.0.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|pad|>

Best Alternatives to LFM2.5 VL 1.6B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 VL 1.6B 4bit0K / 1.5 GB26474
LFM2.5 VL 1.6B 6bit0K / 1.8 GB351
LFM2.5 VL 1.6B0K / 3.2 GB81845313
LFM2.5 VL 1.6B Bf160K / 3.2 GB511
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/LFM2.5-VL-1.6B-8bit.