You can deploy this model and start earning money today!

pramjana/
Qwen3-30B-A3B-Instruct-2507-4bit-GPTQ

Name: Qwen3-30B-A3B-Instruct-2507-4bit-GPTQ
Availability: InStock

Views

No views yet

This is my (first) attempt at quantizing this Qwen3 model (Qwen/Qwen3-30B-A3B-Instruct-2507) using auto-round, like so:

auto-round --model "Qwen/Qwen3-30B-A3B-Instruct-2507" --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.

pramjana/Qwen3-30B-A3B-Instruct-2507-4bit-GPTQ