LLM EXPLORER 65,418 MODELS INDEXED

LFM2.5 24B A2B NVFP4 W4A16 by sapidlabs

By sapidlabs · 239 downloads
HF Repo ↗ Copy URL

LFM2.5 24B A2B NVFP4 W4A16 is an open-source language model by sapidlabs. Features: 24b LLM, VRAM: 14.9GB, Context: 128K, License: other, LLM Explorer Score: 0.31.

  8-bit Base model:liquidai/lfm2.5-24b... Base model:quantized:liquidai/...   Conversational   Dgx-spark   Endpoints compatible   Lfm2.5   Lfm2 moe   Liquid   Modelopt   Nvfp4   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/sapidlabs/LFM2.5-24B-A2B-NVFP4-W4A16 

LFM2.5 24B A2B NVFP4 W4A16 Parameters and Internals

LLM NameLFM2.5 24B A2B NVFP4 W4A16
Repository 🤗https://huggingface.co/sapidlabs/LFM2.5-24B-A2B-NVFP4-W4A16 
Base Model(s)  LiquidAI/LFM2.5-24B-A2B   LiquidAI/LFM2.5-24B-A2B
Model Size24b
Required VRAM14.9 GB
Updated2026-10-22
Maintainersapidlabs
Model Typelfm2_moe
Model Files  1.8 GB: 1-of-10   1.5 GB: 2-of-10   1.5 GB: 3-of-10   1.5 GB: 4-of-10   1.5 GB: 5-of-10   1.5 GB: 6-of-10   1.5 GB: 7-of-10   1.5 GB: 8-of-10   1.5 GB: 9-of-10   1.1 GB: 10-of-10
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 NVFP4 W4A16

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 Preview Bf16128K / 48.2 GB5961
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 sapidlabs/LFM2.5-24B-A2B-NVFP4-W4A16.