Tencent releases WeMM-Video-4B AWQ W4A16 checkpoint
Tencent published a 7.32 GiB AWQ W4A16 Safetensors checkpoint for WeMM-Video-4B. The language model’s feed-forward weights use group-128 INT4, while activations and attention weights remain BF16. The repository provides direct-loading instructions for Transformers 5.2.0 and a serving guide for patched vLLM 0.18.0 with the checkpoint’s compressed-tensors configuration; Transformers loading requires compressed-tensors 0.13.0. Tencent reports that the local checkpoint loaded and completed generation checks for text, images, audio, video frames and video with its soundtrack on one NVIDIA L20 using Transformers 5.2.0 and PyTorch 2.10.0+cu129.
The release documents the checkpoint’s quantization scope and provides instructions for loading and serving it with Transformers and vLLM, giving developers a lower-precision deployment option for WeMM-Video-4B.
tencent/WeMM-Video-4B-AWQ Video-Text-to-Text • 6B • Updated about 4 hours ago • 5
license: apache-2.0 language:
- en
- zh pipeline_tag: video-text-to-text library_name: transformers base_model: tencent/WeMM-Video-4B base_model_relation: quantized tags:
- wemm
- multimodal
- video
- audio
- quantized
- awq
WeMM-Video-4B · AWQ W4A16
Overview
This repository contains the AWQ W4A16 Safetensors variant of WeMM-Video-4B. 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-AWQ#Transformers#vLLM#compressed-tensors#NVIDIA L20#AWQ