Show HN: ExpertCache – Run the Full GPT-OSS 120B (63GB) on a 16GB M1 Pro
Here's a brief summary of the ExpertCache project: ExpertCache is an open-source project that enables the deployment of the full GPT-OSS 120B model, a massive 6
Original sourceHere's a brief summary of the ExpertCache project: ExpertCache is an open-source project that enables the deployment of the full GPT-OSS 120B model, a massive 6
Original source