SenseNova 6.8 Code2Video GSQ RCO needs about 12.9 GB of memory at IQ3_XXS (a 10.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 10.2 GB (IQ3_XXS) to 11.8 GB (IQ3_S). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
SenseNova 6.8 Code2Video GSQ RCO – a lightweight code‑driven video creation model
SenseNova 6.8 Code2Video is a 26.9B‑parameter model fine‑tuned from Qwen3.8‑27B for generating executable code that builds and renders short videos. It supports vision and is released under the Apache‑2.0 license.
Good at
- Code‑driven video generation
- Short video creation
- Programmatic content workflow
Limits
- Requires >12.9 GB VRAM for IQ3_XXS
- No vision support beyond basic image generation
- Long‑horizon runs need explicit context window
Best for
- Creative video scripting
- Rapid prototyping of visual scenes
- Integrating with other generative tools
Who it’s for. Developers and content creators who want to generate video content programmatically. The model is suitable for those who prefer code as the creative medium and need an open, lightweight solution.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 10.2 GB | 12.9 GB | Too big | Get file → | |
| IQ3_S | 11.8 GB | 14.5 GB | Too big | Get file → |
For a 12 GB VRAM budget, use IQ3_XXS (10.2 GB file, 12.9 GB memory at 8 k context). If you have 14 GB VRAM, IQ3_S (11.84 GB file, 14.5 GB memory) offers slightly higher precision. Memory estimates are approximate.
What GPU do you need for SenseNova 6.8 Code2Video GSQ RCO?
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: the best quant that fits is IQ3_S (11.8 GB file, about 14.5 GB in use).
Which SenseNova 6.8 Code2Video GSQ RCO quant should you choose?
IQ3_XXS (10.2 GB) is the middle option in this repository. 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 GSQ RCO
How much VRAM does SenseNova 6.8 Code2Video GSQ RCO need?
About 12.9 GB at IQ3_XXS with an 8K context window. That is the 10.2 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 GSQ RCO on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SenseNova 6.8 Code2Video GSQ RCO GGUF?
It depends on the quant: IQ3_XXS is 10.2 GB, IQ3_S is 11.8 GB.
What context length does SenseNova 6.8 Code2Video GSQ RCO 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 GSQ RCO GGUF?
The files are on Hugging Face in the OliviaRossi/SenseNova-6.8-Code2Video-GSQ-RCO-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 GSQ RCO 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?
No. The smallest quant requires at least 12.9 GB of VRAM at 8 k context.
Does the model support vision tasks?
Yes, it has detected vision abilities for basic image handling.
Is the model open source?
Yes, it is released under the Apache‑2.0 license.