GonzaLomo needs about 15.7 GB of memory at Q6_K (a 12.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 4.7 GB (Q6_K) to 14.6 GB (Q8_0).
GonzaLomo is a 12.8B-parameter Gonzalomo model in GGUF format, quantized by gbrx. Its trained context length is 512 tokens. The repository has 6 quant files, from 4.7 GB (Q6_K) to 14.6 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 4.7 GB | 5.4 GB | Fits | Get file → | |
| Q2_K | 4.8 GB | 5.5 GB | Fits | Get file → | |
| Q6_K | 12.0 GB | 12.7 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 12.7 GB | Too big | Get file → | |
| — | 14.3 GB | 15.0 GB | Too big | Get file → | |
| Q8_0 | 14.6 GB | 15.3 GB | Too big | Get file → |
What GPU do you need for GonzaLomo?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q2_K (4.8 GB file, about 8.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.6 GB file, about 18.3 GB in use).
Which GonzaLomo quant should you choose?
Q6_K (12.0 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q6_K at 4.7 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GonzaLomo
How much VRAM does GonzaLomo need?
About 15.7 GB at Q6_K with an 8K context window. That is the 12.0 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 GonzaLomo on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GonzaLomo GGUF?
It depends on the quant: Q6_K is 4.7 GB, Q2_K is 4.8 GB, Q6_K is 12.0 GB, Q6_K is 12.0 GB, file is 14.3 GB, Q8_0 is 14.6 GB.
What context length does GonzaLomo 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 GonzaLomo GGUF?
The files are on Hugging Face in the gbrx/GonzaLomo repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does GonzaLomo 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.