... everyone Thank you again for the support on AlpieCore , and the feedback from this community meant a lot to us. Since then, we have finally released

... Builders We have just released the official Python SDK and CLI for AlpieCore , our 32B reasoning model trained and served entirely at native 4-bit precision. The goal was simple: make it genuinely easy to build, test, and ship with a reasoning model in real-world systems, not just demos. What s included in the first release: Clean Python SDK with sync, async, and streaming support A lightweight CLI for quick experiments and scripting OpenAI-compatible API surface ... ... Docs + source are live, and we re actively iterating. Github Link: https://github.com/169Pi/Pi169-SDK If you encounter sharp edges, missing primitives, or design gaps, please let us know. This SDK will evolve directly based on how people actually use

... encourage real experimentation, we re offering 5 million free tokens on first API usage so devs and teams can test AlpieCore over Christmas and the New Year.

... While testing AlpieCore beyond benchmarks, we noticed something unexpected. On tasks like step-by-step reasoning, reflective questions, and simple planning ( help me unwind after work , break this problem down calmly ), the model tends to stay unusually structured and neutral. Less fluff, less bias, more explicit reasoning. It made us wonder if training and serving entirely at low precision changes how a model reasons, not just how fast it runs. Sometimes the chain of thought itself is something ...