MiniMax-M3-uncensored · 428B MoE
Study refusal behavior in a 428B multimodal MoE while preserving its reasoning and routing structure.
Every post tagged model-release.
Study refusal behavior in a 428B multimodal MoE while preserving its reasoning and routing structure.
How a 30.7B multimodal Gemma stopped refusing: a deterministic weight-level method, four precision formats, measured refusal and KL results, and serving commands matched to the model cards.
Fit a 34.7B Qwen3.5-MoE reasoning checkpoint onto a single Blackwell workstation without quantizing every subsystem.