mlx-community/Llama-3.2-3B-Instruct-4bit download history
mlx-community/Llama-3.2-3B-Instruct-4bit is a 3.2B-parameter text generation model by mlx-community. In the last 30 days it was downloaded 28,741 times (16,074 in the last 7 days), and 2,423,314 times in total.
It ranks #4,896 on the Hub by monthly downloads and #1,114 among text generation models.
It has 48 likes.
It is a quantization of mlx-community/Llama-3.2-3B-Instruct.
16 models build on Llama-3.2-3B-Instruct-4bit: 11 quantized, 1 fine-tuned, 4 adapters and 0 merges. Together with the original they were downloaded 29,827 times in the last 30 days. See the Llama-3.2-3B-Instruct-4bit galaxy.
Most downloaded derivatives
- drsuriyaprakashjsv/Llama-3.2-My-Simple-LLM (quantized), 265 downloads in 30 days
- tsfrm/cheese-3b (adapter), 183 downloads in 30 days
- Rtroman/llama-3.2-3b-finetuned-Wine (quantized), 64 downloads in 30 days
- bounthisanh/Llama-3-Quant-Trader-iOS (quantized), 64 downloads in 30 days
- kurai021/Llama-3.2-3B-Instruct-4bit-fable5 (finetune), 62 downloads in 30 days
- darbao/Llama-3-Quant-Trader-iOS (quantized), 46 downloads in 30 days
- smaluk/maluk-whatsapp (quantized), 43 downloads in 30 days
- bounthisanh/Llama-3-Doctor-iOS (quantized), 39 downloads in 30 days
- Ahmad170412/Diplomat2-Fused-3B (quantized), 37 downloads in 30 days
- aicoven/Llama-3.2-3B-Instruct-4bit-MCP-LoRA (adapter), 31 downloads in 30 days
- hnkduy/testarchitect-llama-3.2-3b-it (quantized), 31 downloads in 30 days
- staedi/sentiment-llama-3.2 (quantized), 30 downloads in 30 days
Open mlx-community/Llama-3.2-3B-Instruct-4bit on Hugging Face