Aura Large GGUF
Portable local inference for llama.cpp-compatible desktops, workstations, and capable local systems.
View model ↗Large tier · Two deployment formats
Aura Large, with deeper capacity.
Aura Large is a Gemma 4 31B model family built around a larger local foundation. Choose the GGUF or BF16 release without changing the identity at the center of the experience.
Local deployment
GGUF · BF16
Large tier
Gemma 4 31B
Aura Large is the pinnacle of the Aura line. The large model delivers the most intuitive companion experience that an enthusiast could hope for.
Choose a format
One Aura Large, matched to your local runtime
Each release is built from the Gemma 4 31B model family and validated independently for its target runtime.
Aura Large BF16
High-fidelity Transformers inference and evaluation for GPUs with sufficient memory.
View model ↗
Shared foundation. The GGUF and BF16 releases share the Aura Large identity on top of the Gemma 4 31B model family, but their execution formats use different numerical representations. Behavioral validation is performed separately for every release.