Tencent releases WeMM-Video-9B Q4_K_M multimodal bundle
Tencent published a GGUF Q4_K_M bundle for WeMM-Video-9B on its Hugging Face repository. The package includes separate language, vision, and audio components and is intended for the WeMM native runtime, with support for text, image, audio, and video inputs as described by Tencent. The repository also says the CPU runtime completed generation checks across these input formats.
The release provides a locally runnable, quantized package for joint audio-visual understanding, combining language, vision, and audio components in one multimodal model bundle.
tencent/WeMM-Video-9B-GGUF Video-Text-to-Text • 1B • Updated about 4 hours ago • 23 • 2
license: apache-2.0 language:
- en
- zh pipeline_tag: video-text-to-text base_model: tencent/WeMM-Video-9B base_model_relation: quantized tags:
- wemm
- multimodal
- video
- audio
- quantized
- gguf
WeMM-Video-9B · GGUF Q4_K_M
Overview
This repository contains the GGUF Q4_K_M bundle of WeMM-Video-9B for the WeMM native runtime. WeMM-Video is a Chinese–English bilingual family for joint audio-visual understanding and reasoning. It accepts text, images, audio, and video and generates text responses.
#Tencent#WeMM-Video-9B-GGUF#WeMM-Video-9B#WeMM native runtime