valdanito
/

DASD-30B-A3B-Thinking-Preview-FP8-DYNAMIC

Text Generation

compressed-tensors

Model card Files Files and versions

This is Alibaba-Apsara/DASD-30B-A3B-Thinking-Preview quantized with LLM Compressor with FP8 W8A8. The model has been created and tested by The Valdanito. The model is compatible with SGlang v0.5.7. Tested with an NVIDIA H800.

Downloads last month: 1

Safetensors

Model size

31B params

Tensor type

BF16

·

F8_E4M3

·

Model tree for valdanito/DASD-30B-A3B-Thinking-Preview-FP8-DYNAMIC

Base model

Alibaba-Apsara/DASD-30B-A3B-Thinking-Preview

Quantized

(8)

this model