LLM EXPLORER 67,711 MODELS INDEXED

LFM2 24B A2B MLX Bf16 by LiquidAI

By LiquidAI · 80 downloads

LFM2 24B A2B MLX Bf16 is an open-source language model by LiquidAI. Features: 24b LLM, VRAM: 48GB, Context: 125K, License: other, LLM Explorer Score: 0.22.

Base model:finetune:liquidai/l... Base model:liquidai/lfm2-24b-a...   Conversational   En   Lfm2   Lfm2 moe   Liquid   Mlx   Moe   Region:us   Safetensors   Sharded   Tensorflow

LFM2 24B A2B MLX Bf16 Parameters and Internals

LLM NameLFM2 24B A2B MLX Bf16
Repository πŸ€—https://huggingface.co/LiquidAI/LFM2-24B-A2B-MLX-bf16 
Base Model(s)  LFM2 24B A2B   LiquidAI/LFM2-24B-A2B
Model Size24b
Required VRAM48 GB
Updated2026-08-08
MaintainerLiquidAI
Model Typelfm2_moe
Model Files  5.2 GB: 1-of-9   5.4 GB: 2-of-9   5.4 GB: 3-of-9   5.4 GB: 4-of-9   5.4 GB: 5-of-9   5.0 GB: 6-of-9   5.4 GB: 7-of-9   5.4 GB: 8-of-9   5.4 GB: 9-of-9
Supported Languagesen
Model ArchitectureLfm2MoeForCausalLM
Licenseother
Context Length128000
Model Max Length128000
Transformers Version5.0.0rc1
Tokenizer ClassTokenizersBackend
Padding Token<|pad|>
Vocabulary Size65536

Best Alternatives to LFM2 24B A2B MLX Bf16

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 24B A2B128K / 48.3 GB9356424
Diffusion Lfm2.5 24B A2b128K / 96.1 GB16303
LFM2.5 24B A2B FP8128K / 24.6 GB169122
LFM2.5 24B A2B128K / 48.3 GB22438
LFM2.5 24B A2B Base128K / 48.3 GB36235
LFM2.5 24B A2B ONNX128K /  GB54620
LFM2.5 24B A2B MLX Bf16128K / 48.2 GB10736
...usion Lfm2.5 24B A2b Blocktune128K / 48.1 GB622
LFM2.5 24B A2B Preview Bf16128K / 48.2 GB5961
LFM2.5 24B A2B DERISKED BF16128K / 48.3 GB4583
Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2-24B-A2B-MLX-bf16.