TensorFold/GLM-5.3-Flash-MLX-4bit-MTP download history
TensorFold/GLM-5.3-Flash-MLX-4bit-MTP is a 321.3B-parameter image text to text model by TensorFold. In the last 30 days it was downloaded 4,846 times (1,160 in the last 7 days), and 16,548 times in total.
It ranks #12,603 on the Hub by monthly downloads and #1,475 among image text to text models.
It has 15 likes, 1 of them in the last week.
It is a quantization of zai-org/GLM-5.3-Flash.
1 models build on GLM-5.3-Flash-MLX-4bit-MTP: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 5,210 times in the last 30 days. See the GLM-5.3-Flash-MLX-4bit-MTP galaxy.
Most downloaded derivatives
- rapid-mlx/GLM-5.3-Flash-MTP-4bit (quantized), 364 downloads in 30 days
Open TensorFold/GLM-5.3-Flash-MLX-4bit-MTP on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.