New Models

Tencent Releases WeMM-Video-2B-GGUF Quantized Model

Tencent has released the GGUF Q4_K_M quantized version of WeMM-Video-2B, an audio-visual multimodal model supporting ...

New Models

WeMM-Video-2B-NVFP4 Vision-Language Model: 8GB+ VRAM

Explore WeMM-Video-2B-NVFP4, an NVFP4 quantized multimodal large language model by Tencent supporting Chinese and Eng ...