qwenUltrareal needs about 46.3 GB of memory at its main file (a 40.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 40.9 GB to 40.9 GB.
qwenUltrareal is a 20.4B-parameter Qwen model in GGUF format, quantized by Danrisi. The repository has 2 quant files, from 40.9 GB to 40.9 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 40.9 GB | 46.3 GB | Too big | Get file → | |
| — | 40.9 GB | 46.3 GB | Too big | Get file → |
What GPU do you need for qwenUltrareal?
These figures add the file size, an fp16 KV cache at an 8K context window 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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is the main file (40.9 GB file, about 46.3 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about qwenUltrareal
How much VRAM does qwenUltrareal need?
About 46.3 GB at its main file with an 8K context window. That is the 40.9 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 qwenUltrareal on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 46.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of qwenUltrareal GGUF?
It depends on the quant: file is 40.9 GB, file is 40.9 GB.
Where can I download qwenUltrareal GGUF?
The files are on Hugging Face in the Danrisi/qwenUltrareal_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 qwenUltrareal 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.