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

Downloads last month
1
Safetensors
Model size
6.03B 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
Quantized
(15)
this model