Wei Cai 🎮
@weicaiuw
css assistant professor @uw; decentralized computing (crypto + DeAI) researcher @SIGCHI @SIGMM @ACM_SIGWEB; indie game dev @HuluCatsGames
Joined April 2009
763 Following 3K Followers
time to switch to @UnslothAI ?
2.3x faster.
Ran @UnslothAI Qwen3.6 MTP variants on a DGX Spark (UD-Q6_K_XL):
> 27B → 27B MTP: 8.1 → 18.65 t/s (2.3x faster)
> 35B A3B → 35B A3B MTP: 56.91 → 66.52 t/s (+17%)
The 27B dense model more than doubled throughput from MTP alone.
Free speed is free speed.
Show more
