LLM EXPLORER 65,040 MODELS INDEXED

LFM2.5 24B A2B QAD MLX 4bit by Starw1

By Starw1 · 191 downloads
HF Repo ↗ Copy URL

LFM2.5 24B A2B QAD MLX 4bit is an open-source language model by Starw1. Features: 24b LLM, VRAM: 1.6GB, Context: 128K, License: other, Quantized, LLM Explorer Score: 0.3.

  4-bit   4bit Base model:liquidai/lfm2.5-24b... Base model:quantized:liquidai/...   Conversational   Lfm2.5   Lfm2 moe   Liquid   Mlx   Moe   Qad   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Starw1/LFM2.5-24B-A2B-QAD-MLX-4bit 

LFM2.5 24B A2B QAD MLX 4bit Parameters and Internals

LLM NameLFM2.5 24B A2B QAD MLX 4bit
Repository 🤗https://huggingface.co/Starw1/LFM2.5-24B-A2B-QAD-MLX-4bit 
Base Model(s)  LiquidAI/LFM2.5-24B-A2B   LiquidAI/LFM2.5-24B-A2B
Model Size24b
Required VRAM1.6 GB
Updated2026-10-20
MaintainerStarw1
Model Typelfm2_moe
Model Files  4.5 GB   4.5 GB   4.5 GB   1.6 GB
Quantization Type4bit
Model ArchitectureLfm2MoeForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version5.12.1
Tokenizer ClassTokenizersBackend
Padding Token<|pad|>
Vocabulary Size128000
Torch Data Typefloat16

Best Alternatives to LFM2.5 24B A2B QAD MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 24B A2B MLX 6bit128K / 19.5 GB8282
...5 24B A2B Abliterated MLX 4bit128K / 13.5 GB3081
...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
Note: green Score (e.g. "73.2") means that the model is better than Starw1/LFM2.5-24B-A2B-QAD-MLX-4bit.