what do you run this on if I may ask? lmstudio, ollama, lama? which cli?

redwood_ · 2026-02-04T01:53:50 1770170030

I run Qwen3-Coder-Next (Qwen3-Coder-Next-UD-Q4_K_XL) on the Framework ITX board (Max+ 395 - 128GB) custom build. Avg. eval at 200-300 t/s and output at 35-40 t/s running with llama.cpp using rocm. Prefer Claude Code for cli.

Hackbraten · 2026-02-06T10:46:16 1770374776

Curiously, how come you chose -Q4_K_XL instead of -Q8_K_XL?

MrDrMcCoy · 2026-02-04T00:03:07 1770163387

Can't speak for parent, but I've had decent luck with llama.cpp on my triple Ryzen AI Pro 9700 XTs.