Aether-2.2-Pro-GGUF/README.md

library_name, tags, license, language

library_name	tags	license	language
gguf	gguf llama.cpp lm-studio aether german english text-generation	apache-2.0	de en

Aether 2.2 Pro - GGUF

Pre-quantized GGUF binaries for Aether 2.2 Pro.

Trained with SFT (Supervised Fine-Tuning) and PEFT (LoRA) on a custom dataset using local NVIDIA RTX GPU acceleration, Aether 2.2 Pro delivers optimized performance, strong conversational capabilities, and reliable multilingual responses in German and English.

🔗 Looking for the Base / LoRA Adapter? If you want to use the Hugging Face Transformers PEFT adapter instead, check out the main repository: 👉 Maxilicious20/Aether-2.2-Pro

---

📦 Available Files & Quantizations

Choose the right file depending on your system's VRAM/RAM and performance needs:

Filename	Quantization	Quality	Size	Description / Recommendation
aether_2_2_pro_f16.gguf	FP16 / F16	Maximum	~2.88 GB	Uncompressed full precision. Best quality.
aether_2_2_pro_q8_0.gguf	Q8_0	Very High	~1.53 GB	Near-lossless quantization. Excellent balance of precision and speed.
aether_2_2_pro_q4_k_m.gguf	Q4_K_M	Balanced	~940 MB	Recommended. Lightweight, fast, and optimized for low VRAM/RAM setups.

---

🚀 How to Run Locally

1. LM Studio

1. Open LM Studio.
2. Search for Maxilicious20/Aether-2.2-Pro-GGUF or paste the repository ID.
3. Download your preferred quantization (e.g., aether_2_2_pro_q4_k_m.gguf).
4. Load the model and start chatting!

2. Ollama / llama.cpp

You can run the GGUF file directly using llama.cpp:

./llama-cli -m aether_2_2_pro_q4_k_m.gguf -p "Hello Aether Pro!" -n 256