Anyone else getting gibberish when running unsloth/Qwen3.6-35B-A3B-GGUF:UD-IQ4_X... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		cpburns2009 34 days ago \| parent \| context \| favorite \| on: Qwen3.6-35B-A3B: Agentic coding power, now open to... Anyone else getting gibberish when running unsloth/Qwen3.6-35B-A3B-GGUF:UD-IQ4_XS on CUDA (llama.cpp b8815)? UD-Q4_K_XL is fine, as is Vulkan in general.

cpburns2009 34 days ago [–]

Apparently it's a known issue with CUDA 13.2 [1].

[1] https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF/discussi...

danielhanchen 32 days ago | [–]

Yes sadly CUDA 13.2 is broken - NVIDIA will push a fix in CUDA 13.3

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact