top | item 46874276 (no title) organsnyder | 26 days ago They run fairly well for me on my 128GB Framework Desktop. discuss order hn newest mittermayr|26 days ago what do you run this on if I may ask? lmstudio, ollama, lama? which cli? redwood_|26 days 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. load replies (1) MrDrMcCoy|26 days ago Can't speak for parent, but I've had decent luck with llama.cpp on my triple Ryzen AI Pro 9700 XTs.
mittermayr|26 days ago what do you run this on if I may ask? lmstudio, ollama, lama? which cli? redwood_|26 days 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. load replies (1) MrDrMcCoy|26 days ago Can't speak for parent, but I've had decent luck with llama.cpp on my triple Ryzen AI Pro 9700 XTs.
redwood_|26 days 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. load replies (1)
MrDrMcCoy|26 days ago Can't speak for parent, but I've had decent luck with llama.cpp on my triple Ryzen AI Pro 9700 XTs.
mittermayr|26 days ago
redwood_|26 days ago
MrDrMcCoy|26 days ago