This is a MXFP4_MOE quantization of the model InternVL3_5-30B-A3B

Original model: https://huggingface.co/OpenGVLab/InternVL3_5-30B-A3B

Added multimodal projector files I forgot

Downloads last month
70
GGUF
Model size
31B params
Architecture
qwen3moe
Hardware compatibility
Log In to view the estimation

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for noctrex/InternVL3_5-30B-A3B-MXFP4_MOE-GGUF