LLM EXPLORER 58,975 MODELS INDEXED

LFM2.5 8B A1B MLX 4bit by mlx-community

By mlx-community · 520 downloads
HF Repo ↗ Copy URL

LFM2.5 8B A1B MLX 4bit is an open-source language model by mlx-community. Features: 8b LLM, VRAM: 4.8GB, Context: 125K, License: other, Quantized, LLM Explorer Score: 0.26.

  4-bit   4bit   Ar Base model:liquidai/lfm2.5-8b-... Base model:quantized:liquidai/...   Conversational   De   En   Es   Fr   Ja   Ko   Lfm2   Lfm2 moe   Mlx   Moe   Pt   Quantized   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/LFM2.5-8B-A1B-MLX-4bit 

LFM2.5 8B A1B MLX 4bit Parameters and Internals

LLM NameLFM2.5 8B A1B MLX 4bit
Repository 🤗https://huggingface.co/mlx-community/LFM2.5-8B-A1B-MLX-4bit 
Base Model(s)  LiquidAI/LFM2.5-8B-A1B   LiquidAI/LFM2.5-8B-A1B
Model Size8b
Required VRAM4.8 GB
Updated2026-08-10
Maintainermlx-community
Model Typelfm2_moe
Model Files  4.8 GB
Supported Languagesen ar zh fr de ja ko pt es
Quantization Type4bit
Model ArchitectureLfm2MoeForCausalLM
Licenseother
Context Length128000
Model Max Length128000
Transformers Version5.9.0
Tokenizer ClassTokenizersBackend
Padding Token<|pad|>
Vocabulary Size128000

Best Alternatives to LFM2.5 8B A1B MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 8B A1B MLX 8bit125K / 9 GB151429
LFM2.5 8B A1B MLX 4bit125K / 4.8 GB122015
LFM2.5 8B A1B MLX 6bit125K / 6.9 GB4398
LFM2.5 8B A1B MLX 5bit125K / 5.9 GB3068
LFM2.5 8B A1B MLX 8bit125K / 9 GB2775
LFM2 8B A1B 4bit125K / 5.2 GB1979
LFM2 8B A1B 3bit MLX125K / 4.2 GB972
LFM2 8B A1B 8bit MLX125K / 9.4 GB327
LFM2 8B A1B 8bit125K / 9.4 GB293
LFM2 8B A1B 6bit MLX125K / 7.3 GB203
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/LFM2.5-8B-A1B-MLX-4bit.