Tencent releases WeMM-Video-4B GGUF Q4_K_M bundle
Tencent’s WeMM-Video-4B-GGUF repository provides an Apache 2.0-licensed Q4_K_M bundle for the WeMM native runtime. It contains separate language, vision, and audio GGUF components sized at 4.90 GiB, 0.63 GiB, and 2.00 GiB, respectively, and the repository says all three must use the same Hub revision. Tencent describes the model as a Chinese-English bilingual system for joint audio-visual understanding that accepts text, images, audio, and video.
The release provides a concrete GGUF distribution with separate language, vision, and audio components for local use through Tencent’s WeMM native runtime.
tencent/WeMM-Video-4B-GGUF Video-Text-to-Text • 1B • Updated about 4 hours ago • 22 • 3
license: apache-2.0 language:
- en
- zh pipeline_tag: video-text-to-text base_model: tencent/WeMM-Video-4B base_model_relation: quantized tags:
- wemm
- multimodal
- video
- audio
- quantized
- gguf
WeMM-Video-4B · GGUF Q4_K_M
Overview
This repository contains the GGUF Q4_K_M bundle of WeMM-Video-4B 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-4B#WeMM-Video-4B-GGUF#WeMM native runtime