Qwen3-Coder-Next

Re:Qwen3-Coder-Next by organsnyder on Tuesday February 03, 2026 @12:43PM (#46874276)

They run fairly well for me on my 128GB Framework Desktop.

[ Parent | on HN ]

Re:Qwen3-Coder-Next by mittermayr on Tuesday February 03, 2026 @02:51PM (#46876294)

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

[ Parent | on HN ]

Re:Qwen3-Coder-Next by MrDrMcCoy on Tuesday February 03, 2026 @07:03PM (#46879329)

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

[ Parent | on HN ]

Re:Qwen3-Coder-Next by redwood_ on Tuesday February 03, 2026 @08:53PM (#46880395)

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.

[ Parent | on HN ]

Re:Qwen3-Coder-Next by Hackbraten on Friday February 06, 2026 @05:46AM (#46911291)

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

[ Parent | on HN ]