richardyoung/qwen3-32b
TEXT GENERATIONConcurrency Cost:2Model Size:32BQuant:FP8Ctx Length:32kPublished:Nov 18, 2025License:apache-2.0Architecture:Transformer Open Weights Cold

richardyoung/qwen3-32b is a 32-billion parameter uncensored language model based on the Qwen3-32B architecture, developed by Richard Young. It utilizes the Heretic abliteration technique to remove refusal behaviors, allowing it to respond to a broader range of queries without built-in restrictions. With a context length of 40,960 tokens, this model is primarily intended for research, educational purposes, and creative applications where reduced safety guardrails are desired.

Loading preview...