LLM EXPLORER 61,836 MODELS INDEXED

LFM2 2.6B 8bit by mlx-community

By mlx-community · 77 downloads
HF Repo ↗ Copy URL

LFM2 2.6B 8bit is an open-source language model by mlx-community. Features: 2.6b LLM, VRAM: 2.7GB, Context: 125K, License: other, Quantized, LLM Explorer Score: 0.2.

  8-bit   8bit   Ar   Base model:liquidai/lfm2-2.6b Base model:quantized:liquidai/...   Conversational   De   Edge   En   Es   Fr   Ja   Ko   Lfm2   Liquid   Mlx   Quantized   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/LFM2-2.6B-8bit 

LFM2 2.6B 8bit Parameters and Internals

LLM NameLFM2 2.6B 8bit
Repository 🤗https://huggingface.co/mlx-community/LFM2-2.6B-8bit 
Base Model(s)  LiquidAI/LFM2-2.6B   LiquidAI/LFM2-2.6B
Model Size2.6b
Required VRAM2.7 GB
Updated2026-08-06
Maintainermlx-community
Model Typelfm2
Model Files  2.7 GB
Supported Languagesen ar zh fr de ja ko es
Quantization Type8bit
Model ArchitectureLfm2ForCausalLM
Licenseother
Context Length128000
Model Max Length128000
Transformers Version4.55.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size65536
Torch Data Typebfloat16

Best Alternatives to LFM2 2.6B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 2.6B OptiQ 4bit128K / 2 GB3372
LFM2.5 2.6B MLX 8bit128K / 2.9 GB601
LFM2.5 2.6B MLX 6bit128K / 2.2 GB521
LFM2.5 2.6B MLX 5bit128K / 1.9 GB491
LFM2.5 2.6B MLX 4bit128K / 1.6 GB421
LFM2.5 2.6B 4bit125K / 1.5 GB15093
LFM2.5 2.6B 8bit125K / 2.9 GB8543
LFM2 2.6B Exp 4bit125K / 1.4 GB1801
LFM2 2.6B Transcript 4bit125K / 1.4 GB481
LFM2 2.6B Exp 8bit125K / 2.7 GB162
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/LFM2-2.6B-8bit.