← Back to context Comment by mittermayr 7 hours ago what do you run this on if I may ask? lmstudio, ollama, lama? which cli? 2 comments mittermayr Reply redwood_ 31 minutes ago 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. MrDrMcCoy 2 hours ago Can't speak for parent, but I've had decent luck with llama.cpp on my triple Ryzen AI Pro 9700 XTs.
redwood_ 31 minutes ago 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.
MrDrMcCoy 2 hours ago Can't speak for parent, but I've had decent luck with llama.cpp on my triple Ryzen AI Pro 9700 XTs.
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.
Can't speak for parent, but I've had decent luck with llama.cpp on my triple Ryzen AI Pro 9700 XTs.