The A.I. Daily
Home-Trained 0.8B Decision Model Jeff Runs in ~30ms
The independent open project Jeff releases 0.8B and 2B zero-shot decision models fine-tuned from Qwen3.5 and Gemma 4, returning calibrated probabilities in a single forward pass at about 22 ms on an RTX PRO 6000 and 28 ms on an M4 Max, trained only on local hardware with synthetic data and released on Hugging Face.