candle flanUL2 quantized needs about 9.9 GB of memory at its main file (a 8.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.4 GB to 16.0 GB.
candle flanUL2 quantized is a 19.5B-parameter Flan model in GGUF format, quantized by pszemraj. The repository has 4 quant files, from 6.4 GB to 16.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 6.4 GB | 7.7 GB | Tight | Get file → | |
| — | 8.4 GB | 9.9 GB | Too big | Get file → | |
| — | 10.9 GB | 12.8 GB | Too big | Get file → | |
| — | 16.0 GB | 18.4 GB | Too big | Get file → |
What GPU do you need for candle flanUL2 quantized?
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: the best quant that fits is the main file (6.4 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (8.4 GB file, about 9.9 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 12.8 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (16.0 GB file, about 18.4 GB in use).
Which candle flanUL2 quantized quant should you choose?
If memory is tight, the smallest file is the first one in the table at 6.4 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about candle flanUL2 quantized
How much VRAM does candle flanUL2 quantized need?
About 9.9 GB at its main file with an 8K context window. That is the 8.4 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 candle flanUL2 quantized on an 8 GB GPU?
Yes, with the smaller files: the 6.4 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of candle flanUL2 quantized GGUF?
It depends on the quant: file is 6.4 GB, file is 8.4 GB, file is 10.9 GB, file is 16.0 GB.
Where can I download candle flanUL2 quantized GGUF?
The files are on Hugging Face in the pszemraj/candle-flanUL2-quantized repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does candle flanUL2 quantized 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.