k-l-lambda
/

DeepSeek-V3-0324-FP4

8-bit precision

Model card Files Files and versions

DeepSeek-V3-0324-FP4 / README.md

k-l-lambda's picture

initial commit

ec05654 5 months ago

|

history blame contribute delete

203 Bytes

	---
	license: mit
	---
	This is the quantized version of the DeepSeek AI's DeepSeek-V3-0324 model,
	which quantized with [TensorRT Model Optimizer](https://github.com/NVIDIA/TensorRT-Model-Optimizer).