Drop a 9B open-weight model into an agent system built for a frontier cloud model and accuracy falls from 96.0% to 62.3% on PinchBench. Same task. Same tools. Retune the system around the local model. Change the quantization, reasoning loop, tool access, and m

Drop a 9B open-weight model into an agent system built for a frontier cloud model and accuracy falls from 96.0% to 62.3% on PinchBench. Same task. Same tools. Retune the system around the local model. Change the quantization, reasoning loop, tool access, and memory. Accuracy recovers to 88.4%, closing 77% of the gap. The configuration was the limiting factor. Open source, evaluated on Lambda GPUs. 🧵 ↧ Open Jarvis: making local LLMs work as agents Open Jarvis retargets the agent harness around the model, closing 77% of the accuracy gap for local LLMs, at a fraction of the cost and latency of cloud.