LLM EXPLORER 64,561 MODELS INDEXED

LFM2.5 24B A2B Base by LiquidAI

By LiquidAI · 362 downloads
HF Repo ↗ Copy URL

LFM2.5 24B A2B Base is an open-source language model by LiquidAI. Features: 24b LLM, VRAM: 48.3GB, Context: 128K, License: other, LLM Explorer Score: 0.38.

  Arxiv:2511.23404   Ar   Conversational   De   Edge   En   Endpoints compatible   Es   Fr   Hi   Id   It   Ja   Ko   Lfm2.5   Lfm2 moe   Liquid   Moe   Pl   Pt   Region:us   Ru   Safetensors   Sharded   Tensorflow   Th   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-24B-A2B-Base 

LFM2.5 24B A2B Base Parameters and Internals

LLM NameLFM2.5 24B A2B Base
Repository 🤗https://huggingface.co/LiquidAI/LFM2.5-24B-A2B-Base 
Model Size24b
Required VRAM48.3 GB
Updated2026-10-16
MaintainerLiquidAI
Model Typelfm2_moe
Model Files  4.6 GB: 1-of-10   5.0 GB: 2-of-10   5.0 GB: 3-of-10   5.0 GB: 4-of-10   5.0 GB: 5-of-10   5.0 GB: 6-of-10   5.0 GB: 7-of-10   5.0 GB: 8-of-10   5.0 GB: 9-of-10   3.7 GB: 10-of-10
Supported Languagesen ar zh fr de ja ko es pt it vi th id hi ru pl
Model ArchitectureLfm2MoeForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version5.9.0
Tokenizer ClassTokenizersBackend
Padding Token<|pad|>
Vocabulary Size128000

Best Alternatives to LFM2.5 24B A2B Base

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 24B A2B128K / 48.3 GB9356424
LFM2.5 24B A2B FP8128K / 24.6 GB169122
LFM2 24B A2B125K / 47.7 GB13081340
LFM2 24B A2B ONNX125K /  GB9813
LFM2 24B A2B MLX Bf16125K / 48 GB807
LFM2 24B A2B MLX 8bit125K / 25.5 GB16518
LFM2 24B A2B MLX 4bit125K / 13.4 GB18310
LFM2 24B A2B MLX 6bit125K / 19.5 GB1048
LFM2 24B A2B MLX 5bit125K / 16.3 GB846
Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2.5-24B-A2B-Base.