The keeeeenw/MicroLlama galaxy

24 models are built on keeeeenw/MicroLlama: 10 quantized, 14 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 1,808 times in the last 30 days.

Most downloaded direct derivatives

• keeeeenw/MicroLlama-text-embedding (finetune), 235 downloads in 30 days
• mradermacher/MicroLlama-GGUF (quantized), 219 downloads in 30 days
• Felladrin/gguf-MicroLlama (quantized), 211 downloads in 30 days
• balrogbob/microllama-python-instruct-0.3 (finetune), 34 downloads in 30 days
• anilpunjabi/tinyllama_finetuned (finetune), 27 downloads in 30 days
• balrogbob/microllama-python-instruct-0.2 (finetune), 26 downloads in 30 days
• tensorblock/MicroLlama-GGUF (quantized), 25 downloads in 30 days
• balrogbob/microllama-python-instruct-0.1 (finetune), 24 downloads in 30 days
• keeeeenw/MicroLlama-Instruct-0.1 (finetune), 24 downloads in 30 days
• balrogbob/microllama-python-instruct-0.3_4bit (quantized), 22 downloads in 30 days
• anilpunjabi/MicroLlama_finetuned (finetune), 19 downloads in 30 days
• yujiepan/microllama-0.3B (finetune), 16 downloads in 30 days
• Erland/MicroLlama-bnb-4bit (finetune), 14 downloads in 30 days
• Momorami/medusa-microllama_305m_stage1 (finetune), 13 downloads in 30 days
• underactuated/MicroLlama_ft_test (finetune), 8 downloads in 30 days
• Momorami/medusa-microllama_305m_stage2 (finetune), 5 downloads in 30 days
• ballcos/micro_Llama_ko_300m (finetune), 3 downloads in 30 days