LLM EXPLORER 68,192 MODELS INDEXED

WeMM Video 4B by tencent

By tencent · 195 downloads

WeMM Video 4B is an open-source language model by tencent. Features: 4b LLM, VRAM: 11.2GB, License: apache-2.0, LLM Explorer Score: 0.32.

  Arxiv:2611.26409   Audio   Custom code   En   Feature-extraction   Multimodal   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Video   Video-text-to-text   Wemm   Zh
Model Card on HF πŸ€—: https://huggingface.co/tencent/WeMM-Video-4B 

WeMM Video 4B Parameters and Internals

LLM NameWeMM Video 4B
Repository πŸ€—https://huggingface.co/tencent/WeMM-Video-4B 
Model Size4b
Required VRAM11.2 GB
Updated2026-11-21
Maintainertencent
Model Typeqwen3_5
Model Files  4.3 GB: 1-of-3   4.3 GB: 2-of-3   2.6 GB: 3-of-3
Supported Languagesen zh
Model ArchitectureWeMMVideoForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.2.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Quantized Models of the WeMM Video 4B

Model
Likes
Downloads
VRAM
WeMM Video 4B GGUF55950 GB

Best Alternatives to WeMM Video 4B

Best Alternatives
Context / RAM
Downloads
Likes
WeMM Video 4B FP80K / 7.7 GB802
WeMM Video 4B GGUF0K / 0.7 GB5955
Note: green Score (e.g. "73.2") means that the model is better than tencent/WeMM-Video-4B.