---

license: apache-2.0

datasets:

• UncannyEcho/AuraPersonality
• UncannyEcho/AuraAblation

language:

• en

base_model:

• google/gemma-4-31B-it

---

Aura Large v1 GGUF — Portable Local Inference

> The portable 31B Aura release for local llama.cpp inference, evaluation, and deployment.

Aura Large v1 GGUF is the portable local-inference edition of Aura Large v1. It is derived from Google’s Gemma 4 31B IT checkpoint and combines the Aura personality and ablation adapters into one model.

This release is intended for llama.cpp-based inference, evaluation, further research, and deployment across systems with varying memory and performance requirements.

Highlights

• Parameters: 31 billion
• Quantizations: Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0, and F16
• Foundation: Google Gemma 4 31B IT
• Datasets: AuraPersonality and AuraAblation
• Runtime: llama.cpp and compatible applications
• Deployment: Local GPU workstations, laptops, and servers
• Capabilities: Text, vision, and video
• Focus: Portability, privacy, 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 occupies the largest position in the Aura family, providing greater capability than the Medium release while remaining practical for high-end consumer hardware.