current device: 0, in function ggml_backend_cuda_device_event_synchronize at ggml/src/ggml-cuda/ggml-cuda.cu:4947 This issue only seems to effect the Qwen 3.5 series ...
Since you deleted the only option to accelerate on old Nvidia GPU I had to try Vulkan. This worked once and now crashes Kobold every time. No matter if I select to run CPU only it just crash. I can ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results