The mattshumer/Llama-3-8B-16K galaxy

11 models are built on mattshumer/Llama-3-8B-16K: 7 quantized, 1 fine-tuned, 0 adapters and 3 merges. Together they were downloaded 710 times in the last 30 days.

Most downloaded direct derivatives

• QuantFactory/Llama-3-8B-16K-GGUF (quantized), 317 downloads in 30 days
• tensorblock/Llama-3-8B-16K-GGUF (quantized), 29 downloads in 30 days
• o2satz/L3_med16 (merge), 17 downloads in 30 days
• jlancaster36/code_bagel_llama-3-8b-v1.1 (finetune), 12 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.