Umt5 Xxl needs about 7.4 GB of memory at Q4_K_M (a 3.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 10 quants, from 2.9 GB (Q3_K_S) to 22.7 GB (F32).
Umt5 Xxl is a 5.68B-parameter Umt model in GGUF format, quantized by liaqateagle. Its trained context length is 512 tokens. The repository has 10 quant files, from 2.9 GB (Q3_K_S) to 22.7 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 2.9 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_M | 3.1 GB | 3.8 GB | Fits | Get file → | |
| Q4_K_S | 3.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 3.7 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_S | 4.1 GB | 4.8 GB | Fits | Get file → | |
| Q5_K_M | 4.1 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 4.7 GB | 5.4 GB | Fits | Get file → | |
| Q8_0 | 6.0 GB | 6.7 GB | Fits | Get file → | |
| F16 | 11.4 GB | 12.1 GB | Too big | Get file → | |
| F32 | 22.7 GB | 23.4 GB | Too big | Get file → |
What GPU do you need for Umt5 Xxl?
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 Q5_K_M (4.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (6.0 GB file, about 9.8 GB in use).
- 16 GB VRAM: the best quant that fits is F16 (11.4 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (11.4 GB file, about 15.1 GB in use).
- 32 GB VRAM: the best quant that fits is F32 (22.7 GB file, about 26.5 GB in use).
Which Umt5 Xxl quant should you choose?
Q4_K_M is the usual starting point for Umt5 Xxl: it balances file size and quality well. Here it is a 3.7 GB file.
The Q8_0 file is 6.0 GB, about 1.7 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 Q3_K_S at 2.9 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 Umt5 Xxl
How much VRAM does Umt5 Xxl need?
About 7.4 GB at Q4_K_M with an 8K context window. That is the 3.7 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 Umt5 Xxl on an 8 GB GPU?
Yes, with Q5_K_M: the 4.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Umt5 Xxl GGUF?
It depends on the quant: Q3_K_S is 2.9 GB, Q3_K_M is 3.1 GB, Q4_K_S is 3.5 GB, Q4_K_M is 3.7 GB, Q5_K_S is 4.1 GB, Q5_K_M is 4.1 GB and 4 more.
What context length does Umt5 Xxl 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 Umt5 Xxl GGUF?
The files are on Hugging Face in the liaqateagle/umt5-xxl-encoder-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 Umt5 Xxl 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.