Collection needs about 14.7 GB of memory at its main file (a 12.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 12.7 GB to 12.7 GB (Q8_0).
Collection is a 11.9B-parameter Collection model in GGUF format, quantized by Walkearth4. The repository has 2 quant files, from 12.7 GB to 12.7 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 12.7 GB | 14.7 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.7 GB | Too big | Get file → |
What GPU do you need for Collection?
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: the best quant that fits is the main file (12.7 GB file, about 14.7 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Collection
How much VRAM does Collection need?
About 14.7 GB at its main file with an 8K context window. That is the 12.7 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 Collection on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Collection GGUF?
It depends on the quant: file is 12.7 GB, Q8_0 is 12.7 GB.
Where can I download Collection GGUF?
The files are on Hugging Face in the Walkearth4/Collection repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.