LLM EXPLORER 64,924 MODELS INDEXED

LFM2.5 24B A2B MLX 6bit by LiquidAI

By LiquidAI · 828 downloads
HF Repo ↗ Copy URL

LFM2.5 24B A2B MLX 6bit is an open-source language model by LiquidAI. Features: 24b LLM, VRAM: 19.5GB, Context: 128K, License: other, Quantized, LLM Explorer Score: 0.32.

  Arxiv:2511.23404   6-bit   6bit   Ar Base model:liquidai/lfm2.5-24b... Base model:quantized:liquidai/...   Conversational   De   Edge   En   Es   Fr   It   Ja   Ko   Lfm2.5   Lfm2 moe   Liquid   Mlx   Moe   Pt   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-24B-A2B-MLX-6bit 

LFM2.5 24B A2B MLX 6bit Parameters and Internals

LLM NameLFM2.5 24B A2B MLX 6bit
Repository 🤗https://huggingface.co/LiquidAI/LFM2.5-24B-A2B-MLX-6bit 
Base Model(s)  LiquidAI/LFM2.5-24B-A2B   LiquidAI/LFM2.5-24B-A2B
Model Size24b
Required VRAM19.5 GB
Updated2026-10-19
MaintainerLiquidAI
Model Typelfm2_moe
Model Files  5.2 GB: 1-of-4   5.4 GB: 2-of-4   5.4 GB: 3-of-4   3.5 GB: 4-of-4
Supported Languagesen ar zh fr de ja ko es pt it
Quantization Type6bit
Model ArchitectureLfm2MoeForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version5.12.1
Tokenizer ClassTokenizersBackend
Padding Token<|pad|>
Vocabulary Size128000

Best Alternatives to LFM2.5 24B A2B MLX 6bit

Best Alternatives
Context / RAM
Downloads
Likes
...5 24B A2B Abliterated 4bit Mlx128K / 13.5 GB3761
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
LFM2.5 24B A2B128K / 48.3 GB9356424
LFM2.5 24B A2B FP8128K / 24.6 GB169122
LFM2.5 24B A2B Base128K / 48.3 GB36235
...demLLM LFM2.5 24B A2B EXL3 2.5128K / 8.2 GB841
...demLLM LFM2.5 24B A2B EXL3 3.0128K / 9.7 GB821
Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2.5-24B-A2B-MLX-6bit.