FP8-Dynamic Quant of TheDrummer/Cydonia-24B-v4.1

FP8-Dynamic quant of TheDrummer/Cydonia-24B-v4.1 using llm-compressor for quantization.

Downloads last month
10
Safetensors
Model size
24B 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 ArtusDev/TheDrummer_Cydonia-24B-v4.1-FP8-Dynamic

Quantized
(18)
this model