# WeMM-Video-35BA3B

> WeMM-Video-35B-A3B is the mixture-of-experts (35B total, 3B active) 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:** 36.2B total, 5B active (MoE)
- **Context length:** 262,144 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-11-17
- **Hugging Face:** 239 downloads (30 days), 27 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 12.76 |
| Q3_K_M | 18.42 |
| Q4_K_M | 22.57 |
| Q5_K_M | 26.29 |
| Q6_K | 30.27 |
| Q8_0 | 38.71 |
| F16 | 71.88 |

## 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)
- [MLX](https://github.com/ml-explore/mlx-lm) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

WeMM-Video-35B-A3B is the mixture-of-experts (35B total, 3B active) 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 · 67.39 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/Qwen3.6-35B-A3B](https://selfhost.directory/models/qwen/qwen3.6-35b-a3b) (36B (3B active), Apache 2.0, ≈22.44 GB at Q4): Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding…
- [openbmb/MiniCPM-V-4.7-35B-A3B](https://selfhost.directory/models/openbmb/minicpm-v-4.7-35b-a3b) (35.2B (3B active), Apache 2.0, ≈22 GB at Q4): GitHub · On-device results · Evaluation · Examples · Usage · Model weights
- [Qwen/Qwen3.8-27B](https://selfhost.directory/models/qwen/qwen3.8-27b) (27.8B, Apache 2.0, ≈18.97 GB at Q4): Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.
- [google/gemma-4-31B-it](https://selfhost.directory/models/google/gemma-4-31b-it) (31.3B, Apache 2.0, ≈26.54 GB at Q4): Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
- [Qwen/Qwen3.5-35B-A3B](https://selfhost.directory/models/qwen/qwen3.5-35b-a3b) (36B (3B active), Apache 2.0, ≈22.44 GB at Q4): Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
- [Qwen/Qwen3.6-27B](https://selfhost.directory/models/qwen/qwen3.6-27b) (27.8B, Apache 2.0, ≈18.97 GB at Q4): Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding…

More: https://selfhost.directory/models/tencent/wemm-video-35ba3b/alternatives

## Runs well on

- [Tesla P40](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/tesla-p40): Q4_K_M, est. 63 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/rx-7900-xtx): Q4_K_M, est. 175 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/instinct-mi50): Q6_K, est. 138 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/rtx-5090): Q6_K, est. 241 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/apple-m4-pro-48gb): Q6_K, est. 37 tok/s
- [RTX A6000](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/rtx-a6000): Q8_0, est. 80 tok/s

## Similar size

- [Qwen/Qwen3.8-27B](https://selfhost.directory/models/qwen/qwen3.8-27b) (27.8B)
- [google/gemma-4-31B-it](https://selfhost.directory/models/google/gemma-4-31b-it) (31.3B)
- [Qwen/Qwen3.6-35B-A3B](https://selfhost.directory/models/qwen/qwen3.6-35b-a3b) (36B)
- [google/gemma-4-26B-A4B-it](https://selfhost.directory/models/google/gemma-4-26b-a4b-it) (25.8B)
- [Qwen/Qwen3.6-27B](https://selfhost.directory/models/qwen/qwen3.6-27b) (27.8B)
- [Qwen/Qwen3.5-35B-A3B](https://selfhost.directory/models/qwen/qwen3.5-35b-a3b) (36B)

## FAQ

**How much VRAM does WeMM-Video-35BA3B need?**
About 23 GB at Q4_K_M with an 8K context. Q8_0 needs about 39 GB and full precision about 72 GB. Longer contexts need more memory for the KV cache.

**Can WeMM-Video-35BA3B run on the Tesla P40?**
Yes. It fits at Q4_K_M (about 23 GB), at an estimated 63 tokens/s. It fits comfortably on the Radeon RX 7900 XTX, Instinct MI50 32GB, RTX 5090.

**Can I use WeMM-Video-35BA3B 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-35BA3B?**
262,144 tokens (256K). The full window needs far more memory than an 8K context.

## Links

- huggingface: https://huggingface.co/tencent/WeMM-Video-35BA3B
- github: https://github.com/Tencent/WeMM-Video
- paper: https://arxiv.org/abs/2611.26409

---
Source: https://selfhost.directory/models/tencent/wemm-video-35ba3b