Gryphe/Pantheon-Reasoning-27B · Hugging Face

Article automatically generated from technical news.

from Gryphe: An experiment in bringing reasoning capability to the Pantheon roleplay series in the form of an uncensored dense Qwen 3.6 27B. This specific model can be thought of as a successor to both the Pantheon series and the one-time Codex release since I used such a large variety of data this time around. Yet another theory being tested this time around: take the data that Pantheon is built on, pair it with full thinking traces, and let the model reason its way through