MTPLX V2.10 sudah keluar!

I put a lot of work into this one. Highlights: - Qwen 3.8 Next Support Added: Bare Speed (4 bit) and Optimised Speed (4 bit/8 bit) models added running at 50 - 80 TPS sustained at high contexts. (expect speed improvements in the coming days) - Qwen 3.8

Youssof Al ToukhiAug 29134

Qwen 3.8 max Sangat buruk (mode tidak berpikir)

Abhishek sharmaAug 29

Membuat video pendek tentang pengaturan pengkodean getaran pengembang solo terbaik ⚡️

OMP + Qwen 3.8 for building apps DeepSeek Flash V4 for vision One developer + an AI coding stack = seriously powerful. The solo dev era is getting wild.

StackDripAug 291

Saya akan menarik postingan aslinya terlebih dahulu agar penulisan ulangnya bisa sesuai dengan panjangnya

Structure, and meaning.The post quotes an article and includes a video, so I’m checking both before rewriting.ABSURD. Qwen 3.8 27B is running locally on an RTX 4060 with just 8GB of VRAM. That's a 64k

RaoulDukeAug 293