The rinna/llama-3-youko-8b galaxy

30 models are built on rinna/llama-3-youko-8b: 18 quantized, 2 fine-tuned, 2 adapters and 8 merges. Together they were downloaded 43,104 times in the last 30 days.

Most downloaded direct derivatives

• lmg-anon/vntl-llama3-8b-v2-gguf (quantized), 34.9K downloads in 30 days
• mradermacher/llama-3-youko-8b-GGUF (quantized), 772 downloads in 30 days
• QuantFactory/llama-3-youko-8b-GGUF (quantized), 585 downloads in 30 days
• featherless-ai-quants/rinna-llama-3-youko-8b-GGUF (quantized), 438 downloads in 30 days
• rinna/llama-3-youko-8b-instruct (merge), 355 downloads in 30 days
• csabakecskemeti/rinna.llama-3-youko-8b-GGUF (quantized), 239 downloads in 30 days
• rinna/llama-3-youko-8b-gptq (quantized), 58 downloads in 30 days
• RichardErkhov/rinna_-_llama-3-youko-8b-4bits (quantized), 49 downloads in 30 days
• tensorblock/llama-3-youko-8b-GGUF (quantized), 45 downloads in 30 days
• adslvmke/vntl-llama3-8b-v2-gguf (quantized), 30 downloads in 30 days
• lmg-anon/vntl-llama3-8b-v2-hf (finetune), 15 downloads in 30 days
• minhhien0811/llama3-8b-ja (finetune), 9 downloads in 30 days
• lmg-anon/vntl-llama3-8b-qlora (adapter), 6 downloads in 30 days
• lmg-anon/vntl-llama3-8b-hf (adapter), 0 downloads in 30 days