Running local LLMs on your NPU with FastFlowLM
For Copilot+ PCs, FastFlowLM leverages the NPU to run local LLMs beyond the built-in Copilot features: think Ollama, but on your NPU.
Anyone who wants to utilize their NPUs beyond the in-built Copilot features on Copilot+ PCs to run local LLMs, FastFlowLM is a great resource. It leverages the NPU to deliver performance for local LLMs. Think of it as Ollama, but using your NPU.
Video: FastFlow + Open WebUI and NPU actually being useful.