Gemma 4 31B uncensored · format family
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.
Every post tagged nvfp4.
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.