Saya menyambungkan API Qwen-3.8-Max-0902 langsung ke alur kerja pengkodean saya.

Jangan khawatir... Tidak ada pengaturan yang mewah. Karena Anda dapat menggunakannya dengan Agen Pengodean AI apa pun Ini pengaturan saya 👇 Kode VS + Cline + Qwen. Karena saya sudah menggunakan VS Code dari awal 😅 Saya memberinya tugas pengkodean yang nyata…

Faith MudashiSep 16

Ok. Qwen 3.8 Next Q3, 7900xtx 64gbddr5.

Linux outpaces Windows by .5 toks on best configs running on my Chonk Buffer llama. 19.8 t/s Linux vs 19.34 best recipe. Full offload linux 15.4 vs 15.5. Was kind of surprised. Expected more but my zero overhead protocols 🦾 14 toks at 262k

ChonkESep 166

Every inference engine kind of runs on vibes.

I got Qwen 3.8 already running on this modest tab BTW, however I'm trying to pool as many ops/fixes to the OpenCL backend as possible. has the fixes in opencl-fixes and qwen38-fixes cc: ggerganov

Karthik Kumar ViswanathanSep 163

Qwen 3.8 flash next built this landing page in 29 minutes and served it on my tailnet on its own.

I am running official fp8 on 2x dgx spark, full 256k context loaded, 45 tok/s with mtp on. i have run deepseek and glm on these boxes and it was good, this one just feels right.

Sudo suSep 1663