alt Hacker NewsOh I didn't expect this to be on HN haha - but yes for our new benchmarks for Qwen3.5, we devised a slightly different approach for quantization which we plan to roll out to all new models from now on!
Replies
hedora • yesterday at 6:26 PM
Nice! Your stuff ran LLMs extremely well on < $500 boxes (24-32GB ram) with iGPUS before this update.
I’m eager to try it out, especially if 16GB is viable now.
Can you describe what is this slightly different approach and why it should work on all models?