cpatonn/OpenReasoning-Nemotron-32B-AWQ-4bit

OpenReasoning-Nemotron-32B-AWQ

Method

Quantised using casper-hansen/AutoAWQ and the following configs:

quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }