LLM EXPLORER 64,924 MODELS INDEXED

LFM2.5 24B A2B Abliterated 4bit Mlx by Jakevin

By Jakevin · 376 downloads
HF Repo ↗ Copy URL

LFM2.5 24B A2B Abliterated 4bit Mlx is an open-source language model by Jakevin. Features: 24b LLM, VRAM: 13.5GB, Context: 128K, License: other, Quantized, LLM Explorer Score: 0.31.

  4-bit   4bit   Abliterated Base model:liquidai/lfm2.5-24b... Base model:quantized:liquidai/...   Conversational   Lfm2   Lfm2 moe   Mlx   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Uncensored
Model Card on HF 🤗: https://huggingface.co/Jakevin/LFM2.5-24B-A2B-abliterated-4bit-mlx 

LFM2.5 24B A2B Abliterated 4bit Mlx Parameters and Internals

LLM NameLFM2.5 24B A2B Abliterated 4bit Mlx
Repository 🤗https://huggingface.co/Jakevin/LFM2.5-24B-A2B-abliterated-4bit-mlx 
Base Model(s)  LiquidAI/LFM2.5-24B-A2B   LiquidAI/LFM2.5-24B-A2B
Model Size24b
Required VRAM13.5 GB
Updated2026-10-19
MaintainerJakevin
Model Typelfm2_moe
Model Files  5.4 GB: 1-of-3   5.3 GB: 2-of-3   2.8 GB: 3-of-3
Quantization Type4bit
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 Abliterated 4bit Mlx

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 24B A2B MLX 6bit128K / 19.5 GB8282
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 Jakevin/LFM2.5-24B-A2B-abliterated-4bit-mlx.