isogen
/

OpenReasoning-Nemotron-14B-exl3-6bpw

Model card Files Files and versions

EXL3 quantization of OpenReasoning-Nemotron-14B, 6 bits per weight.

Downloads last month: -

Safetensors

Model size

6B params

Tensor type

F16

·

I16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for isogen/OpenReasoning-Nemotron-14B-exl3-6bpw

Base model

Qwen/Qwen2.5-14B

Finetuned

nvidia/OpenReasoning-Nemotron-14B

Quantized

(16)

this model