SenseNova 6.8 Code2Video MTP needs about 21.2 GB of memory at Q4_K_M (a 18.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 15.1 GB (IQ3_M) to 29.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
SenseNova 6.8 Code2Video MTP – a 27.3B code‑driven video creation model
SenseNova 6.8 Code2Video MTP is a 27.3B hybrid qwen35 model fine‑tuned for generating executable code that builds and renders short videos. It supports reasoning, tools and vision, and includes a 1‑layer Multi‑Token Prediction head for speculative decoding.
Good at
- Code‑driven video generation
- Multimodal vision support
- Long‑horizon creative workflows
Limits
- No vision beyond code‑driven rendering
- Requires large VRAM for higher quants
- Apache‑2.0 license limits commercial use without attribution
Best for
- Short programmatic video creation
- Tool‑calling creative pipelines
- Educational demonstrations of code‑to‑video
Who it’s for. Developers and researchers interested in programmatic video creation and multimodal code generation. The model is suitable for those who want to experiment with code‑driven workflows and integrate multiple generative tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_M | 15.1 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_M | 15.8 GB | 18.5 GB | Too big | Get file → | |
| IQ4_XS | 17.2 GB | 19.8 GB | Too big | Get file → | |
| Q4_K_S | 17.5 GB | 20.2 GB | Too big | Get file → | |
| Q4_K_M | 18.5 GB | 21.2 GB | Too big | Get file → | |
| Q5_K_M | 20.6 GB | 23.3 GB | Too big | Get file → | |
| Q6_K | 22.9 GB | 25.6 GB | Too big | Get file → | |
| Q8_0 | 29.0 GB | 31.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ3_M (15.09 GB file, 17.8 GB memory). For 12 GB VRAM, Q3_K_M (15.81 GB file, 18.5 GB memory) is suitable. For 16 GB VRAM, Q4_K_M (18.48 GB file, 21.2 GB memory) offers a good balance of quality and memory usage. All estimates are approximate.
What GPU do you need for SenseNova 6.8 Code2Video MTP?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q5_K_M (20.6 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).
Which SenseNova 6.8 Code2Video MTP quant should you choose?
Q4_K_M is the usual starting point for SenseNova 6.8 Code2Video MTP: it balances file size and quality well. Here it is a 18.5 GB file.
The Q8_0 file is 29.0 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ3_M at 15.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SenseNova 6.8 Code2Video MTP
How much VRAM does SenseNova 6.8 Code2Video MTP need?
About 21.2 GB at Q4_K_M with an 8K context window. That is the 18.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run SenseNova 6.8 Code2Video MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SenseNova 6.8 Code2Video MTP GGUF?
It depends on the quant: IQ3_M is 15.1 GB, Q3_K_M is 15.8 GB, IQ4_XS is 17.2 GB, Q4_K_S is 17.5 GB, Q4_K_M is 18.5 GB, Q5_K_M is 20.6 GB and 2 more.
What context length does SenseNova 6.8 Code2Video MTP support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download SenseNova 6.8 Code2Video MTP GGUF?
The files are on Hugging Face in the Abiray/SenseNova-6.8-Code2Video-MTP-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SenseNova 6.8 Code2Video MTP use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run SenseNova 6.8 Code2Video on 8 GB VRAM?
Use the IQ3_M quant, which requires about 17.8 GB of VRAM at 8 k context. 8 GB VRAM is insufficient for this model.
Does the model support image generation?
Yes, it includes an F16 Multimodal Vision Projector for vision tasks, but the primary focus is code‑driven video creation.
Is the model licensed for commercial use?
The model is under the Apache‑2.0 license, which permits commercial use with attribution.