my model collection needs about 6.1 GB of memory at Q4_0 (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 8 quants, from 0.1 GB (IQ4_NL) to 9.2 GB (Q3_K_M).
my model collection is a 219M-parameter Model model in GGUF format, quantized by Rayquaza04. The repository has 8 quant files, from 0.1 GB (IQ4_NL) to 9.2 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q5_K_M | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q4_0 | 5.0 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_M | 7.2 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_M | 7.2 GB | 8.5 GB | Too big | Get file → | |
| Q5_K_S | 8.5 GB | 10.1 GB | Too big | Get file → | |
| Q3_K_M | 9.2 GB | 10.8 GB | Too big | Get file → |
What GPU do you need for my model 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: the best quant that fits is F16 (0.8 GB file, about 1.4 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_K_M (4.1 GB file, about 5.1 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_0 (5.0 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_M (9.2 GB file, about 10.8 GB in use).
Which my model collection quant should you choose?
Q4_0 (5.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ4_NL at 0.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about my model collection
How much VRAM does my model collection need?
About 6.1 GB at Q4_0 with an 8K context window. That is the 5.0 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 my model collection on an 8 GB GPU?
Yes, with Q4_0: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of my model collection GGUF?
It depends on the quant: IQ4_NL is 0.1 GB, F16 is 0.8 GB, Q5_K_M is 4.1 GB, Q4_0 is 5.0 GB, Q3_K_M is 7.2 GB, Q3_K_M is 7.2 GB and 2 more.
Where can I download my model collection GGUF?
The files are on Hugging Face in the Rayquaza04/my_model_collection repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.