https://github.com/ollama/ollama/issues/11772 A year and still no implementation for such a basic need as offloading MoE layers onto the CPU selectively. On llama.cpp I can get models like Qwen 35BA3B running partially…
https://github.com/ollama/ollama/issues/11772 A year and still no implementation for such a basic need as offloading MoE layers onto the CPU selectively. On llama.cpp I can get models like Qwen 35BA3B running partially…