mlx-community/Llama-3.2-1B-Instruct-4bit download history
mlx-community/Llama-3.2-1B-Instruct-4bit is a 1.2B-parameter text generation model by mlx-community. In the last 30 days it was downloaded 33,440 times (7,022 in the last 7 days), and 7,681,704 times in total.
It ranks #4,581 on the Hub by monthly downloads and #1,044 among text generation models.
It has 21 likes.
It is a quantization of mlx-community/Llama-3.2-1B-Instruct-bf16.
9 models build on Llama-3.2-1B-Instruct-4bit: 7 quantized, 0 fine-tuned, 2 adapters and 0 merges. Together with the original they were downloaded 33,720 times in the last 30 days. See the Llama-3.2-1B-Instruct-4bit galaxy.
Most downloaded derivatives
- aniruddhabagal/fraud-sentinel-1b (adapter), 162 downloads in 30 days
- DiyRex/Llama-3.2-1B-nl2bash (adapter), 32 downloads in 30 days
- tqiqbal/llama-masna (quantized), 27 downloads in 30 days
- getonit/transcription-ef-llama3.2-1b (quantized), 17 downloads in 30 days
- sheenrooff/Llama-3.2-1B-Instruct-4bit-ff-test (quantized), 11 downloads in 30 days
- jarkas/jilid_llama_1b_4bit_v2 (quantized), 9 downloads in 30 days
- jarkas/jilid_llama_1b_4bit_v1 (quantized), 8 downloads in 30 days
- jarkas/jilid_llama_1b_4bit_v3 (quantized), 7 downloads in 30 days
- sheenrooff/Llama-3.2-1B-Instruct-4bit-adapters-ff-test (quantized), 7 downloads in 30 days
Open mlx-community/Llama-3.2-1B-Instruct-4bit on Hugging Face