LLM EXPLORER 57,252 MODELS INDEXED

LFM2.5 8B A1B MLX Bf16 by LiquidAI

By LiquidAI · 359 downloads
HF Repo ↗ Copy URL

LFM2.5 8B A1B MLX Bf16 is an open-source language model by LiquidAI. Features: 8b LLM, VRAM: 16.8GB, Context: 125K, License: other, LLM Explorer Score: 0.27.

  Arxiv:2511.23404   Ar Base model:finetune:liquidai/l... Base model:liquidai/lfm2.5-8b-...   Conversational   De   Edge   En   Es   Fr   Ja   Ko   Lfm2.5   Lfm2 moe   Liquid   Mlx   Moe   Pt   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-MLX-bf16 

LFM2.5 8B A1B MLX Bf16 Parameters and Internals

LLM NameLFM2.5 8B A1B MLX Bf16
Repository 🤗https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-MLX-bf16 
Base Model(s)  LiquidAI/LFM2.5-8B-A1B   LiquidAI/LFM2.5-8B-A1B
Model Size8b
Required VRAM16.8 GB
Updated2026-08-08
MaintainerLiquidAI
Model Typelfm2_moe
Model Files  5.2 GB: 1-of-4   5.1 GB: 2-of-4   5.1 GB: 3-of-4   1.4 GB: 4-of-4
Supported Languagesen ar zh fr de ja ko es pt
Model ArchitectureLfm2MoeForCausalLM
Licenseother
Context Length128000
Model Max Length128000
Transformers Version5.2.0
Tokenizer ClassTokenizersBackend
Padding Token<|pad|>
Vocabulary Size128000

Best Alternatives to LFM2.5 8B A1B MLX Bf16

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 8B A1B125K / 16.9 GB84755670
LFM2.5 8B A1B Base125K / 16.9 GB420129
...inal ToolBench Full SFT 1Epoch125K / 16.9 GB88672
LFM2 8B A1B125K / 16.7 GB30570370
LFM2.5 8B A1B Opus Distil125K / 16.9 GB21275
LFM2.5 8B A1B125K / 16.9 GB124013
LFM2.5 8B A1B NVFP4125K / 6.9 GB4607
Supertron2.1 8B A1B125K / 17 GB966
LFM2.5 8B A1B ONNX125K /  GB7911
LFM2.5 8B A1B KO CPT FULL125K / 16.9 GB381
Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2.5-8B-A1B-MLX-bf16.