Upaya kedua pada pengeditan ini

Made with Terresect. Qwen 3.8 27b on a Single RTX 6000

WbackdownSep 251

Qwen 3.8 + ltx 2.5

⛏️🌱Don Kackman 🌱⛏️Sep 25

Karena semua orang mengirim spam ke gulungan bodoh itu.

Qwen 3.8 27B, Kimi K3, Mimo V2.6 flash and astra Xhigh. obviously astra won. Mimi was surprising. kimi did no audio and...qwen is qwen

That one belgian 🖤☕ VmanagerSep 25

Untuk iseng saya mencoba memberikan tugas ini kepada GLM 5.3 Flash (Kiri) dan Qwen 3.8 27b ThinkingCap (Kanan).

Both decided to use Python with PIL and numpy. Much, much simpler, but Qwen's pretty decent for a 27b model, just hope it wasn't destroyed by compression

NoctreSep 25