Sulphur 2 Prompt Enhancer Uncensored needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.4 GB (IQ4_NL) to 5.6 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Uncensored prompt enhancer for Sulphur 2 video generation
Sulphur 2 Prompt Enhancer Uncensored converts short prompts into detailed video generation prompts for LTX 2.3 / Sulphur‑2. It is based on the qwen35 architecture and supports vision. The model is released under the apache‑2.0 license.
Good at
- Vision‑enabled prompt enhancement
- Uncensored video generation prompts
- Compatibility with LTX 2.3 formats
Limits
- No official inference yet
- Requires 8 k context for memory estimates
- No system prompt needed
Best for
- Enhancing prompts for video generation
- Using with ComfyUI or LM Studio
- Integrating with Sulphur‑2 base models
Who it’s for. Developers and content creators who need detailed prompts for LTX 2.3 video generation. The model is suitable for those working with Sulphur‑2 and its prompt‑enhancer workflow.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 5.4 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → |
For an 8 k context, the IQ4_NL quant requires about 7 GB of VRAM and the Q4_K_M quant about 7.2 GB. Choose IQ4_NL for a slightly smaller file size of 5.44 GB, or Q4_K_M for a marginally larger 5.63 GB file if you prefer the latter quantization.
What GPU do you need for Sulphur 2 Prompt Enhancer Uncensored?
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: the best quant that fits is Q4_K_M (5.6 GB file, about 7.2 GB in use).
Which Sulphur 2 Prompt Enhancer Uncensored quant should you choose?
Q4_K_M is the usual starting point for Sulphur 2 Prompt Enhancer Uncensored: it balances file size and quality well. Here it is a 5.6 GB file.
If memory is tight, the smallest file is IQ4_NL at 5.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sulphur 2 Prompt Enhancer Uncensored
How much VRAM does Sulphur 2 Prompt Enhancer Uncensored need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Sulphur 2 Prompt Enhancer Uncensored on an 8 GB GPU?
Yes, with Q4_K_M: the 5.6 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sulphur 2 Prompt Enhancer Uncensored GGUF?
It depends on the quant: IQ4_NL is 5.4 GB, Q4_K_M is 5.6 GB.
What context length does Sulphur 2 Prompt Enhancer Uncensored support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Sulphur 2 Prompt Enhancer Uncensored GGUF?
The files are on Hugging Face in the PeppX/Sulphur-2-Prompt-Enhancer-Uncensored-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 Sulphur 2 Prompt Enhancer Uncensored 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 this model on 8 GB VRAM?
Yes, the IQ4_NL quant uses approximately 7 GB of VRAM at 8 k context, which fits within an 8 GB GPU. The Q4_K_M quant uses about 7.2 GB.
Does this model support vision?
Yes, the model has detected vision abilities and can process images as part of the prompt enhancement.
Is there a system prompt required?
No, the prompt enhancer does not use a system prompt; simply send the text and image you want enhanced.