Aura Large v1.1 BF16 — High-Fidelity Transformers
The high-fidelity 31B Aura release for Transformers inference, evaluation, and research.
Aura Large v1.1 BF16 is the full-precision merged edition of Aura Large v1.1. It is derived from Google’s Gemma 4 31B IT checkpoint and combines the Aura personality and ablation adapters into one model.
The v1.1 release has seen significant improvements to the personality adapter, merged and applied with the same ablation adapter as v1.
This release is intended for Transformers-based inference, evaluation, further research, and deployment on GPUs with sufficient memory.
Highlights
- Parameters: 31 billion
- Precision: BFloat16
- Foundation: Google Gemma 4 31B IT
- Datasets: AuraPersonality and AuraAblation
- Runtime: Hugging Face Transformers
- Deployment: Local GPU workstations and servers
- Capabilities: Text, vision, and video
- Focus: Fidelity, natural conversation, evaluation, and research
About Aura
Aura is designed for local and on-device deployment across multiple tasks. Aura can serve as a companion or friend, as deemed appropriate by the user, while retaining the broader capabilities of Gemma 4 for:
- Natural conversation
- Creative writing
- Reasoning
- Image understanding
- Video understanding
- Tool use
- Evaluation and research
Aura Large v1.1 occupies the largest position in the Aura family, providing greater capability than the Medium release while remaining practical for high-end consumer hardware.