# WeVisCut

> WeVisCut is a 9B tool-using agent that turns knowledge articles or narration scripts into multi-minute edited videos. At each step, it reads the current editing state and selects one of 12 tools for planning, narration, asset retrieval, composition, inspection, or repair.

- **Organisation:** tencent
- **Category:** Omni / Any-to-Any
- **Parameters:** 9.4B
- **Context length:** 262,144 tokens
- **Licence:** Custom licence (Check licence)
- **Released:** 2026-09-09
- **Hugging Face:** 16.7K downloads (30 days), 30 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 4.53 |
| Q3_K_M | 6 |
| Q4_K_M | 7.08 |
| Q5_K_M | 8.04 |
| Q6_K | 9.08 |
| Q8_0 | 11.28 |
| F16 | 19.9 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [SGLang](https://selfhost.directory/project/sglang)
- [Transformers](https://github.com/huggingface/transformers)
- [vLLM](https://selfhost.directory/project/vllm)

## About

WeVisCut is a 9B tool-using agent that turns knowledge articles or narration scripts into multi-minute edited videos. At each step, it reads the current editing state and selects one of 12 tools for planning, narration, asset retrieval, composition, inspection, or repair. It is not a standalone text-to-video model; use it with the WeVisCut runtime, which executes the model's tool calls.

Requirements: Python 3.11 or later and an NVIDIA GPU with about 24 GB of memory for bf16 inference. Install a PyTorch build compatible with your CUDA version before the GPU requirements below. The setup script installs Node.js, FFmpeg, and the renderer.

Open http:// :8081/ to use the Studio. For UI-only mode without loading model weights, run bash run_studio.sh --no-model.

The policy is based on Qwen3.5-9B and is trained on executable editing trajectories. Its runtime provides an editable timeline with pause/resume, manual and chat-based revisions, per-shot rerendering, and version rollback. Video quality depends on the configured retrieval, TTS, and rendering services and available templates.

WeVisCut is intended for research and production assistance in long-form video editing. It does not guarantee factual accuracy or production quality; review generated narration and video before publication. The model weights require the WeVisCut tool environment to produce a video.

## Alternatives

- [google/gemma-4-E4B-it](https://selfhost.directory/models/google/gemma-4-e4b-it) (8B, Apache 2.0, ≈5.9 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.
- [google/gemma-4-12B-it](https://selfhost.directory/models/google/gemma-4-12b-it) (12B, Apache 2.0, ≈10.59 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.
- [openbmb/MiniCPM-o-4_5](https://selfhost.directory/models/openbmb/minicpm-o-4_5) (9.4B, Apache 2.0, ≈7.18 GB at Q4): A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone
- [google/gemma-4-E4B](https://selfhost.directory/models/google/gemma-4-e4b) (8B, Apache 2.0, ≈5.9 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.
- [google/gemma-4-E2B-it](https://selfhost.directory/models/google/gemma-4-e2b-it) (5.1B, Apache 2.0, ≈3.81 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.
- [nvidia/music-flamingo-hf](https://selfhost.directory/models/nvidia/music-flamingo-hf) (8.3B, Custom licence, ≈5.84 GB at Q4): Music Flamingo (MF) is a fully open, state-of-the-art Large Audio-Language Model (LALM) designed to advance music (including song) understanding in foundational audio models. MF brings together innovations in:

More: https://selfhost.directory/models/tencent/weviscut/alternatives

## Runs well on

- [GeForce RTX 4060](https://selfhost.directory/models/tencent/weviscut/on/rtx-4060): Q4_K_M, est. 26 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/tencent/weviscut/on/apple-m4-16gb): Q6_K, est. 8.5 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/tencent/weviscut/on/rx-6700-xt): Q8_0, est. 21 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/tencent/weviscut/on/rtx-3060): Q8_0, est. 20 tok/s
- [Arc B580](https://selfhost.directory/models/tencent/weviscut/on/arc-b580): Q8_0, est. 25 tok/s
- [Tesla T4](https://selfhost.directory/models/tencent/weviscut/on/tesla-t4): Q8_0, est. 18 tok/s

## Similar size

- [google/gemma-4-E4B-it](https://selfhost.directory/models/google/gemma-4-e4b-it) (8B)
- [google/gemma-4-12B-it](https://selfhost.directory/models/google/gemma-4-12b-it) (12B)
- [openbmb/MiniCPM-o-4_5](https://selfhost.directory/models/openbmb/minicpm-o-4_5) (9.4B)
- [Qwen/Qwen2.5-Omni-7B](https://selfhost.directory/models/qwen/qwen2.5-omni-7b) (10.7B)
- [google/gemma-3n-E4B-it](https://selfhost.directory/models/google/gemma-3n-e4b-it) (7.8B)
- [nvidia/audio-flamingo-3-hf](https://selfhost.directory/models/nvidia/audio-flamingo-3-hf) (8.3B)

## FAQ

**How much VRAM does WeVisCut need?**
About 7.1 GB at Q4_K_M with an 8K context. Q8_0 needs about 11 GB and full precision about 20 GB. Longer contexts need more memory for the KV cache.

**Can WeVisCut run on the RTX 4060?**
Yes. It fits at Q4_K_M (about 7.0 GB), at an estimated 26 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.

**Can I use WeVisCut commercially?**
Unclear. It is released under Custom licence. Custom licence: read the model card before using it commercially. Check the licence on the model card before using it in a product.

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

**How do I run WeVisCut with llama.cpp?**
Run llama-server -hf prithivMLmods/tencent-WeVisCut-GGUF:Q4_K_M. It downloads the GGUF and starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/tencent/WeVisCut
- github: https://github.com/Tencent/WeVisCut
- paper: https://arxiv.org/abs/2610.38352

---
Source: https://selfhost.directory/models/tencent/weviscut