pramjana/Qwen3-14B-4bit-GPTQ

This is my (first) attempt at quantizing this Qwen3 model (Qwen/Qwen3-14B) using auto-round, like so:

auto-round --model "Qwen/Qwen3-14B" --scheme "W4A16" --format "auto_gptq" --output_dir "./Quantized" --model_dtype fp16

The primary purpose of these quants are to make them run on consumer AMD GPUs, which they do work, in my case.