Tencent releases FP8 checkpoint for WeMM-Video-35B-A3B
Tencent’s Hugging Face model repository lists a new FP8 Block128 Safetensors variant of WeMM-Video-35B-A3B under the ID tencent/WeMM-Video-35BA3B-FP8. The checkpoint is based on the quantized 35B-A3B model, uses Apache-2.0 licensing, and contains 36.09 GiB of weight files. Tencent says the bilingual model accepts text, images, audio, and video, with loading and generation checks reported on an NVIDIA L20 and H20.
This release gives developers an openly licensed FP8 build and documented Transformers and patched vLLM workflows for running Tencent’s multimodal audio-video model.
tencent/WeMM-Video-35BA3B-FP8 Video-Text-to-Text • 36B • Updated about 6 hours ago • 5
license: apache-2.0 language:
- en
- zh pipeline_tag: video-text-to-text library_name: transformers base_model: tencent/WeMM-Video-35BA3B base_model_relation: quantized tags:
- wemm
- multimodal
- video
- audio
- quantized
- fp8
- moe
WeMM-Video-35B-A3B · FP8 Block128
Overview
This repository contains the FP8 Block128 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-35B-A3B#Transformers#vLLM#NVIDIA L20#NVIDIA H20#Safetensors