The rinna/gemma-2-baku-2b galaxy

24 models are built on rinna/gemma-2-baku-2b: 13 quantized, 1 fine-tuned, 2 adapters and 8 merges. Together they were downloaded 5,505 times in the last 30 days.

Most downloaded direct derivatives

• QuantFactory/gemma-2-baku-2b-it-GGUF (merge), 894 downloads in 30 days
• mradermacher/gemma-2-baku-2b-i1-GGUF (quantized), 369 downloads in 30 days
• lmg-anon/vntl-gemma2-2b-gguf (adapter), 324 downloads in 30 days
• rinna/gemma-2-baku-2b-it (merge), 224 downloads in 30 days
• DevQuasar-10/rinna.gemma-2-baku-2b-GGUF (quantized), 219 downloads in 30 days
• tensorblock/gemma-2-baku-2b-GGUF (quantized), 185 downloads in 30 days
• mradermacher/gemma-2-baku-2b-GGUF (quantized), 121 downloads in 30 days
• mlx-community/gemma-2-baku-2b-it-4bit (merge), 56 downloads in 30 days
• mlx-community/gemma-2-baku-2b-it (merge), 42 downloads in 30 days
• mlx-community/gemma-2-baku-2b-it-8bit (merge), 42 downloads in 30 days
• sehiro/gemma-2-baku-2b-Q4_K_M-GGUF (quantized), 19 downloads in 30 days
• Sakalti/Gemma-2-Baku-Finetune (finetune), 15 downloads in 30 days
• lmg-anon/vntl-gemma2-2b-lora (adapter), 12 downloads in 30 days