This is LFM2.5-1.2B-Thinking quantized with llm-compressor to MXFP4. The model is compatible with vLLM (tested: v0.14.0; still experimental). Tested with an L4 (Google Colab).

Downloads last month
10
Safetensors
Model size
0.8B params
Tensor type
BF16
·
U8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kaitchup/LFM2.5-1.2B-Thinking-MXFP4

Quantized
(23)
this model

Collection including kaitchup/LFM2.5-1.2B-Thinking-MXFP4