The mlx-community/Llama-3.2-1B-Instruct-bf16 galaxy

19 models are built on mlx-community/Llama-3.2-1B-Instruct-bf16: 14 quantized, 1 fine-tuned, 4 adapters and 0 merges. Together they were downloaded 35,651 times in the last 30 days.

Most downloaded direct derivatives

• mlx-community/Llama-3.2-1B-Instruct-4bit (quantized), 33.4K downloads in 30 days
• featherless-ai-quants/mlx-community-Llama-3.2-1B-Instruct-bf16-GGUF (quantized), 458 downloads in 30 days
• tensorblock/mlx-community_Llama-3.2-1B-Instruct-bf16-GGUF (quantized), 80 downloads in 30 days
• Koutouzov1973/Llama-3.2-1B-Instruct-4bit_Essai (quantized), 38 downloads in 30 days
• hellowsherlock/theranotes-Llama-3.2-1B-Instruct-4bit (quantized), 28 downloads in 30 days
• squishai/Llama-3.2-1B-Instruct-bf16-squished (quantized), 23 downloads in 30 days
• asksolz/munin-llama32-1b-4bit-mlx (quantized), 21 downloads in 30 days
• Leighlo/llama-finetuned-pre-gguf (finetune), 4 downloads in 30 days
• yashcse21/text2sql-llama1b-adapters-caution (adapter), 0 downloads in 30 days
• yashcse21/text2sql-llama1b-final-cot-lr5e-5-l16-i2500 (adapter), 0 downloads in 30 days