GNER T5 xxl encoder only needs about 13.2 GB of memory at its main file (a 9.5 GB file) with an 8K context window, so it fits on a 16 GB GPU.
GNER T5 xxl encoder only is a 4.76B-parameter Gner model in GGUF format, quantized by wikeeyang. Its trained context length is 512 tokens. The repository has 1 quant file, from 9.5 GB to 9.5 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 9.5 GB | 10.2 GB | Too big | Get file → |
What GPU do you need for GNER T5 xxl encoder only?
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 the main file (9.5 GB file, about 13.2 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GNER T5 xxl encoder only
How much VRAM does GNER T5 xxl encoder only need?
About 13.2 GB at its main file with an 8K context window. That is the 9.5 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 GNER T5 xxl encoder only on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GNER T5 xxl encoder only GGUF?
It depends on the quant: file is 9.5 GB.
What context length does GNER T5 xxl encoder only support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 3.2 GB at 8K and 0.2 GB at 512.
Where can I download GNER T5 xxl encoder only GGUF?
The files are on Hugging Face in the wikeeyang/GNER-T5-xxl-encoder-only repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does GNER T5 xxl encoder only 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.