mlx-community/Qwen2.5-14B-Instruct-1M-8bit download history

mlx-community/Qwen2.5-14B-Instruct-1M-8bit is a 14.8B-parameter text generation model by mlx-community. In the last 30 days it was downloaded 217 times (56 in the last 7 days), and 4,171 times in total.

It ranks #130,212 on the Hub by monthly downloads and #33,357 among text generation models.

It has 12 likes.

It is a quantization of Qwen/Qwen2.5-14B-Instruct-1M.

2 models build on Qwen2.5-14B-Instruct-1M-8bit: 2 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 249 times in the last 30 days. See the Qwen2.5-14B-Instruct-1M-8bit galaxy.

Most downloaded derivatives

• parole-study-viper/speech-to-sql (quantized), 20 downloads in 30 days
• parole-study-viper/vulgarity-filter (quantized), 12 downloads in 30 days

Open mlx-community/Qwen2.5-14B-Instruct-1M-8bit on Hugging Face