zlacker
[parent]
[thread]
3 comments
1. organs+(OP)
[view]
[source]
2026-02-03 17:43:06
They run fairly well for me on my 128GB Framework Desktop.
replies(1):
>>mitter+yw
◧
2. mitter+yw
[view]
[source]
2026-02-03 19:51:17
>>organs+(OP)
what do you run this on if I may ask? lmstudio, ollama, lama? which cli?
replies(2):
>>MrDrMc+vj1
>>redwoo+HA1
◧◩
3. MrDrMc+vj1
[view]
[source]
[discussion]
2026-02-04 00:03:07
>>mitter+yw
Can't speak for parent, but I've had decent luck with llama.cpp on my triple Ryzen AI Pro 9700 XTs.
◧◩
4. redwoo+HA1
[view]
[source]
[discussion]
2026-02-04 01:53:50
>>mitter+yw
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.
[go to top]