This is LFM2.5-1.2B-JP quantized with llm-compressor to NVFP4. The model is compatible with vLLM (tested: v0.13.0). Tested with an RTX 4090.

How to Support My Work

"buy me a kofi" Subscribe to The Kaitchup. This helps me a lot to continue quantizing and evaluating models for free.

Safetensors

Model size

0.9B params

Tensor type

F32

BF16

F8_E4M3

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including kaitchup/LFM2.5-1.2B-JP-NVFP4