Tencent releases WeMM-Video-35B-A3B GGUF bundle
Tencent’s WeMM-Video model repository introduced an Apache-2.0 GGUF Q4_K_M bundle for WeMM-Video-35B-A3B, with separate language, vision, and audio components. The repository says the WeMM native CPU runtime loaded the bundle and completed generation checks for text, images, audio, and video with a soundtrack; Tencent describes the model family as Chinese-English bilingual and capable of joint audio-visual understanding and reasoning.
The release provides a native-runtime deployment option for a multimodal model with separate language, vision, and audio components, while its bilingual and multimodal capabilities remain vendor-described.
tencent/WeMM-Video-35BA3B-GGUF Video-Text-to-Text • 1B • Updated about 6 hours ago • 5 • 2
license: apache-2.0 language:
- en
- zh pipeline_tag: video-text-to-text base_model: tencent/WeMM-Video-35BA3B base_model_relation: quantized tags:
- wemm
- multimodal
- video
- audio
- quantized
- gguf
- moe
WeMM-Video-35B-A3B · GGUF Q4_K_M
Overview
This repository contains the GGUF Q4_K_M bundle of WeMM-Video-35B-A3B 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.