This is LFM2.5-1.2B-Thinking quantized with llm-compressor to FP8. The model is compatible with vLLM (tested: v0.14.0). Tested with an L4 (Google Colab).

Downloads last month
38
Safetensors
Model size
1B params
Tensor type
BF16
·
F8_E4M3
·
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-FP8-Dynamic

Quantized
(22)
this model

Collection including kaitchup/LFM2.5-1.2B-Thinking-FP8-Dynamic