isogen
/

OpenReasoning-Nemotron-7B-exl3-8bpw-h8

8-bit precision

Model card Files Files and versions

OpenReasoning-Nemotron-7B-exl3-8bpw-h8 / README.md

isogen's picture

Upload folder using huggingface_hub

029a953 verified about 2 months ago

|

history blame contribute delete

251 Bytes

	---
	base_model: nvidia/OpenReasoning-Nemotron-7B
	---

	[EXL3](https://github.com/turboderp-org/exllamav3) quantization of [OpenReasoning-Nemotron-7B](https://huggingface.co/nvidia/OpenReasoning-Nemotron-7B), 8 bits per weight, including output layers.