The Dampfinchen/Llama-3.1-8B-Ultra-Instruct galaxy

178 models are built on Dampfinchen/Llama-3.1-8B-Ultra-Instruct: 113 quantized, 6 fine-tuned, 0 adapters and 59 merges. Together they were downloaded 59,463 times in the last 30 days.

Most downloaded direct derivatives

• bartowski/Llama-3.1-8B-Ultra-Instruct-GGUF (quantized), 3.6K downloads in 30 days
• QuantFactory/LLama-3.1-Hyper-Stock-GGUF (merge), 1.7K downloads in 30 days
• mradermacher/Llama-3.1-8B-Ultra-Instruct-i1-GGUF (quantized), 1K downloads in 30 days
• featherless-ai-quants/Dampfinchen-Llama-3.1-8B-Ultra-Instruct-GGUF (quantized), 634 downloads in 30 days
• mradermacher/Llama-3.1-8B-Ultra-Instruct-GGUF (quantized), 256 downloads in 30 days
• tensorblock/Llama-3.1-8B-Ultra-Instruct-GGUF (quantized), 56 downloads in 30 days
• bunnycore/LLama-3.1-8b-Ultra-Max-Pro (merge), 25 downloads in 30 days
• bunnycore/Llama-3.1-8B-TitanFusion-v2 (merge), 18 downloads in 30 days
• cstr/llama3.1-8b-spaetzle-v59-GGUF (quantized), 16 downloads in 30 days
• Dampfinchen/Llama-3.1-8B-Ultra-Instruct-Q4_K_S-GGUF (quantized), 14 downloads in 30 days
• bunnycore/LLama-3.1-Hyper-Stock (merge), 14 downloads in 30 days
• cstr/llama3.1-8b-spaetzle-v59 (finetune), 10 downloads in 30 days