Tencent publishes NVFP4 WeMM-Video-35B-A3B checkpoint
Tencent published the WeMM-Video-35BA3B-NVFP4 checkpoint, an NVFP4 W4A16 Safetensors variant of WeMM-Video-35B-A3B with 24.11 GiB of weight files. The model card says it supports Chinese and English audio-visual understanding, accepting text, images, audio, and video, and includes instructions for serving it with patched vLLM 0.31.0, ModelOpt Mixed Precision, and Marlin.
This is a substantive open checkpoint release that adds a quantized deployment option for a 35B-A3B video-text-to-text model, although the reported capabilities are vendor-provided.
tencent/WeMM-Video-35BA3B-NVFP4 Video-Text-to-Text • 36B • Updated about 6 hours ago • 3 • 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
- nvfp4
- moe
WeMM-Video-35B-A3B · NVFP4 W4A16
Overview
This repository contains the NVFP4 W4A16 Safetensors variant of WeMM-Video-35B-A3B. 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-35BA3B-NVFP4#WeMM-Video-35B-A3B#vLLM#ModelOpt#Marlin