Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Yes they are quite good, but are not able to run on a 16GB RX 9070.

Quantized Qwen 3.8 Flash Next could maybe run eventually on that card with a highly optimized inference engine that dynamically caches the hottest layer experts. Even then you run into some hard limits.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: