# WeMM-Video-9B

> WeMM-Video-9B is the dense 9B checkpoint in the WeMM-Video family. 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.

- **Organisation:** tencent
- **Category:** Vision-Language Models
- **Parameters:** 10.5B
- **Context length:** 262,144 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-11-17
- **Hugging Face:** 230 downloads (30 days), 10 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 4.87 |
| Q3_K_M | 6.51 |
| Q4_K_M | 7.72 |
| Q5_K_M | 8.8 |
| Q6_K | 9.95 |
| Q8_0 | 12.4 |
| F16 | 22.01 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [LM Studio](https://lmstudio.ai)
- [Transformers](https://github.com/huggingface/transformers)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

WeMM-Video-9B is the dense 9B checkpoint in the WeMM-Video family. 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.

• Weights · BF16 Safetensors · 19.54 GiB of weight files
• Quantized variants · FP8 Block128 · AWQ W4A16 · GGUF Q4_K_M · NVFP4 W4A16

WeMM-Video can combine video frames with the original soundtrack to describe events, transcribe speech, and reason about what is seen and heard. It also accepts silent video, standalone audio, images, and text, with responses in Chinese or English.

Vision and audio encoders turn media into tokens that the language model processes alongside text. Video frames carry timestamps. The family was pretrained on approximately 1.2 trillion multimodal tokens, then post-trained with multi-teacher OPD, anti-repetition MrDPO, and specialist reinforcement learning.

See the project overview for family details.

Set up the Transformers environment. From the WeMM-Video repository root, run the example on an MP4 with a soundtrack. The script loads the model and processor from the Hub and processes both the frames and the original audio track.

Use --revision to pin the model and processor to a Hub commit. Size GPU memory for the full weight files, media inputs, and generation cache.

## Alternatives

- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b) (9.7B, Apache 2.0, ≈7.22 GB at Q4): Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct) (8.8B, Apache 2.0, ≈6.82 GB at Q4): Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
- [Zyphra/ZAYA1-VL-8B](https://selfhost.directory/models/zyphra/zaya1-vl-8b) (9.7B, Apache 2.0, ≈6.58 GB at Q4): ZAYA1-VL-8B is a vision-language model (VLM) built upon Zyphra's ZAYA1-8B LLM. It has state-of-the-art performance among VLMs for its size and inference efficiency.
- [omlab/VLX-Seek-1.5-10B](https://selfhost.directory/models/omlab/vlx-seek-1.5-10b) (10B, Apache 2.0, ≈7.44 GB at Q4): VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios.
- [Qwen/Qwen3.5-9B-Base](https://selfhost.directory/models/qwen/qwen3.5-9b-base) (9.7B, Apache 2.0, ≈7.22 GB at Q4): Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
- [XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://selfhost.directory/models/xiaomimimo/mimo-v2.6-distill-qwen-9b) (9.4B, MIT, ≈7.08 GB at Q4): MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model developed by Xiaomi MiMo through supervised fine-tuning of Qwen3.5-9B on MiMo-generated data. It covers coding, general-purpose agent tasks, visual coding, and cybersecurity.

More: https://selfhost.directory/models/tencent/wemm-video-9b/alternatives

## Runs well on

- [Apple M4 (16 GB)](https://selfhost.directory/models/tencent/wemm-video-9b/on/apple-m4-16gb): Q6_K, est. 7.6 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/tencent/wemm-video-9b/on/rx-6700-xt): Q6_K, est. 24 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/tencent/wemm-video-9b/on/rtx-3060): Q6_K, est. 23 tok/s
- [Arc B580](https://selfhost.directory/models/tencent/wemm-video-9b/on/arc-b580): Q6_K, est. 29 tok/s
- [Tesla T4](https://selfhost.directory/models/tencent/wemm-video-9b/on/tesla-t4): Q8_0, est. 16 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/tencent/wemm-video-9b/on/arc-a770): Q8_0, est. 28 tok/s

## Similar size

- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b) (9.7B)
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct) (8.8B)
- [Qwen/Qwen2.5-VL-7B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-vl-7b-instruct) (8.3B)
- [google/gemma-3-12b-it](https://selfhost.directory/models/google/gemma-3-12b-it) (12.2B)
- [XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://selfhost.directory/models/xiaomimimo/mimo-v2.6-distill-qwen-9b) (9.4B)
- [meta-llama/Llama-3.2-11B-Vision-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-11b-vision-instruct) (10.7B)

## FAQ

**How much VRAM does WeMM-Video-9B need?**
About 7.7 GB at Q4_K_M with an 8K context. Q8_0 needs about 12 GB and full precision about 22 GB. Longer contexts need more memory for the KV cache.

**Can WeMM-Video-9B run on the RTX 3060 12GB?**
Yes. It fits at Q6_K (about 9.9 GB), at an estimated 23 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, Arc B580.

**Can I use WeMM-Video-9B commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**What is the context length of WeMM-Video-9B?**
262,144 tokens (256K). The full window needs far more memory than an 8K context.

## Links

- huggingface: https://huggingface.co/tencent/WeMM-Video-9B
- github: https://github.com/Tencent/WeMM-Video
- paper: https://arxiv.org/abs/2611.26409

---
Source: https://selfhost.directory/models/tencent/wemm-video-9b