Trained with SFT (Supervised Fine-Tuning) and PEFT (LoRA) on a custom 3 GB dataset using local NVIDIA RTX GPU acceleration, Aether 2.3 delivers high intelligence, robust conversational capabilities, and exceptional multilingual performance 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-2.3

📦 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_3_fp16.gguf`	FP16 / F16	Maximum	~5.75 GB	Uncompressed full precision. Best quality, requires more VRAM.
`aether_2_3_q8_0.gguf`	Q8_0	Very High	~3.05 GB	Near-lossless quantization. Excellent balance of precision and speed.
`aether_2_3_q4_k_m.gguf`	Q4_K_M	Balanced	~1.79 GB	Recommended. Best compromise between speed, size, and minimal quality loss.

🚀 How to Run Locally

1. LM Studio

Open LM Studio.
Search for Maxilicious20/Aether-2.3-GGUF or paste the repo ID.
Download your preferred quantization (e.g., aether_2_3_q4_k_m.gguf).
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_3_q4_k_m.gguf -p "Hello Aether!" -n 256

Maxilicious20/Aether-2.3-GGUF

Aether 2.3 - GGUF

📦 Available Files & Quantizations

🚀 How to Run Locally

1. LM Studio

2. Ollama / llama.cpp

Maxilicious20/
Aether-2.3-GGUF