LLM EXPLORER 65,418 MODELS INDEXED

LFM2.5 24B A2B Preview Bf16 by mlx-community

By mlx-community · 596 downloads
HF Repo ↗ Copy URL

LFM2.5 24B A2B Preview Bf16 is an open-source language model by mlx-community. Features: 24b LLM, VRAM: 48.2GB, Context: 128K, License: other, LLM Explorer Score: 0.31.

  Ar   Conversational   De   En   Es   Fr   It   Ja   Ko   Lfm2.5   Lfm2 moe   Mlx   Mlx-vlm   Moe   Pt   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/LFM2.5-24B-A2B-Preview-bf16 

LFM2.5 24B A2B Preview Bf16 Parameters and Internals

LLM NameLFM2.5 24B A2B Preview Bf16
Repository 🤗https://huggingface.co/mlx-community/LFM2.5-24B-A2B-Preview-bf16 
Base Model(s)  lq-preview/LFM2.5-24B-A2B-Preview   lq-preview/LFM2.5-24B-A2B-Preview
Model Size24b
Required VRAM48.2 GB
Updated2026-10-22
Maintainermlx-community
Model Typelfm2_moe
Model Files  5.0 GB: 1-of-10   5.4 GB: 2-of-10   5.4 GB: 3-of-10   5.4 GB: 4-of-10   5.4 GB: 5-of-10   5.4 GB: 6-of-10   5.0 GB: 7-of-10   5.4 GB: 8-of-10   5.4 GB: 9-of-10   0.4 GB: 10-of-10
Supported Languagesen ar zh fr de ja ko es pt it
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 Preview Bf16

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 24B A2B128K / 48.3 GB9356424
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
LFM2.5 24B A2B NVFP4 W4A16128K / 14.9 GB2391
LFM2.5 24B A2B NVFP4A16128K / 0.3 GB2301
... 24B A2B DERISKED EXL3 3.25bpw128K / 10.4 GB1301
...demLLM LFM2.5 24B A2B EXL3 2.5128K / 8.2 GB1241
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/LFM2.5-24B-A2B-Preview-bf16.