---

license: apache-2.0

datasets:

• UncannyEcho/AuraPersonality
• UncannyEcho/AuraAblation

language:

• en

base_model:

• google/gemma-4-12B-it

---

Aura Medium v1.1 GGUF — Portable Local Inference

> The portable 12B Aura release for local llama.cpp inference, evaluation, and deployment.

Aura Medium v1.1 GGUF is the portable local-inference edition of Aura Medium v1.1. It is derived from Google’s Gemma 4 12B 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 llama.cpp-based inference, evaluation, further research, and deployment across systems with varying memory and performance requirements.

Highlights

• Parameters: 12 billion
• Quantizations: Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0, and F16
• Foundation: Google Gemma 4 12B IT
• Datasets: AuraPersonality and AuraAblation
• Runtime: llama.cpp and compatible applications
• Deployment: Local GPU workstations, laptops, and servers
• Capabilities: Text, vision, audio, 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
• Audio and video understanding
• Tool use
• Evaluation and research

Aura Medium v1.1 occupies the middle position in the Aura family, providing greater capability than the compact E4B release while remaining practical for high-end consumer hardware.