soberano1 needs about 22.6 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 19.8 GB (Q4_K_M) to 65.5 GB.
soberano1 is a 32.8B-parameter Soberano model in GGUF format, quantized by soberania. Its trained context length is 40K tokens. The repository has 5 quant files, from 19.8 GB (Q4_K_M) to 65.5 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 19.8 GB | 22.6 GB | Too big | Get file → | |
| Q8_0 | 34.8 GB | 39.5 GB | Too big | Get file → | |
| Q8_0 | 34.8 GB | 39.5 GB | Too big | Get file → | |
| — | 65.5 GB | 73.9 GB | Too big | Get file → | |
| — | 65.5 GB | 73.9 GB | Too big | Get file → |
What GPU do you need for soberano1?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (19.8 GB file, about 22.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (19.8 GB file, about 22.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 39.5 GB in use).
Which soberano1 quant should you choose?
Q4_K_M is the usual starting point for soberano1: it balances file size and quality well. Here it is a 19.8 GB file.
The Q8_0 file is 34.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about soberano1
How much VRAM does soberano1 need?
About 22.6 GB at Q4_K_M with an 8K context window. That is the 19.8 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 soberano1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of soberano1 GGUF?
It depends on the quant: Q4_K_M is 19.8 GB, Q8_0 is 34.8 GB, Q8_0 is 34.8 GB, file is 65.5 GB, file is 65.5 GB.
What context length does soberano1 support?
The GGUF header lists a trained context length of 40,960 tokens (40K).
Where can I download soberano1 GGUF?
The files are on Hugging Face in the soberania/soberano1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.