Saya mendapat peningkatan kecepatan 200% di Qwen 3.8 Flash Selanjutnya, sekarang 28-24tok/detik di ram ddr4 64gb dan 3090.
Sekitar 11 tok/s ketika saya pertama kali memulai, saya yakin DDR5 akan menjadi lebih cepat. Cafe-llama.cpp bukan hanya satu garpu lagi.
A free 27B Chinese AI model can now analyze your SEO research, videos, documents, workflows, and code.
But the interesting part isn't that it's free. It's what happens when you give Qwen 3.8-27B your entire business context.
Qwen 3.8 unhinged is actually more wikd than I expected 😳
Qwen 3.8 takes a little longer to think things through...
Also Qwen 3.8:
Sudah sampai ujung arsip
Semua qwen38