Garbage 9B iMatrix needs about 7.3 GB of memory at its main file (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 8 quants, from 2.5 GB to 18.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Garbage 9B iMatrix is a 8.99B-parameter Garbage model in GGUF format, quantized by MarsupialAI. Its trained context length is 32K tokens. The repository has 8 quant files, from 2.5 GB to 18.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.5 GB | 4.3 GB | Fits | Get file → | |
| — | 3.5 GB | 5.3 GB | Fits | Get file → | |
| — | 4.8 GB | 6.7 GB | Fits | Get file → | |
| — | 5.4 GB | 7.3 GB | Tight | Get file → | |
| — | 6.4 GB | 8.2 GB | Too big | Get file → | |
| — | 7.4 GB | 9.2 GB | Too big | Get file → | |
| — | 9.6 GB | 11.4 GB | Too big | Get file → | |
| — | 18.0 GB | 19.8 GB | Too big | Get file → |
What GPU do you need for Garbage 9B iMatrix?
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: the best quant that fits is the main file (3.5 GB file, about 5.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (5.4 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (9.6 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (9.6 GB file, about 11.4 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (18.0 GB file, about 19.8 GB in use).
Which Garbage 9B iMatrix quant should you choose?
If memory is tight, the smallest file is the first one in the table at 2.5 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 Garbage 9B iMatrix
How much VRAM does Garbage 9B iMatrix need?
About 7.3 GB at its main file with an 8K context window. That is the 5.4 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 Garbage 9B iMatrix on an 8 GB GPU?
Yes, with the smaller files: the 5.4 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Garbage 9B iMatrix GGUF?
It depends on the quant: file is 2.5 GB, file is 3.5 GB, file is 4.8 GB, file is 5.4 GB, file is 6.4 GB, file is 7.4 GB and 2 more.
What context length does Garbage 9B iMatrix support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Garbage 9B iMatrix GGUF?
The files are on Hugging Face in the MarsupialAI/Garbage_9B_iMatrix_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 Garbage 9B iMatrix 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.