Re:If AI writes your code, why use Python?
by 2ndorderthought on Tuesday May 12, 2026 @01:23PM
(#48111336)
Is that on a single 3090? I need to change my settings it sounds like
Re:If AI writes your code, why use Python?
by johndough on Tuesday May 12, 2026 @04:05PM
(#48113726)
Yes, single RTX 3090 with this model https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-h... following these https://huggingface.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF instructions (should add "-j 8" to last cmake command for parallel build)
and llama-server with --reasoning off
Note that the MTP PR https://github.com/ggml-org/llama.cpp/pull/22673 is still under development, so things might be broken.
I've found that the Q5+ quants are less loopy than Q4. Still not perfect, but noticeably better.
> reasonable enough tokens per second
The speed has been amazing. I've been running the recent llama.cpp MTP branch with an uncensored variant of Qwen3.6-35B-A3B on my RTX 3090 over 170 tokens per second and it was able to turn a buffer overflow into a reliable shell exploit in just a few seconds (with reasoning disabled). Still a bit loopy though. Hopefully, the Qwen team will pay more attention to those looping issues. It feels like their models are especially susceptible.