SeFi Image 5B turbo needs about 4.8 GB of memory at Q5_1 (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.2 GB (Q4_1) to 5.3 GB (Q8_0).
SeFi Image 5B turbo is a 4.97B-parameter Sefi model in GGUF format, quantized by Sam2x. The repository has 3 quant files, from 3.2 GB (Q4_1) to 5.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_1 | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q5_1 | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q8_0 | 5.3 GB | 6.5 GB | Fits | Get file → |
What GPU do you need for SeFi Image 5B turbo?
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: the best quant that fits is Q5_1 (3.8 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.3 GB file, about 6.5 GB in use).
Which SeFi Image 5B turbo quant should you choose?
Q5_1 (3.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_1 at 3.2 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 SeFi Image 5B turbo
How much VRAM does SeFi Image 5B turbo need?
About 4.8 GB at Q5_1 with an 8K context window. That is the 3.8 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 SeFi Image 5B turbo on an 8 GB GPU?
Yes, with Q8_0: the 5.3 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SeFi Image 5B turbo GGUF?
It depends on the quant: Q4_1 is 3.2 GB, Q5_1 is 3.8 GB, Q8_0 is 5.3 GB.
Where can I download SeFi Image 5B turbo GGUF?
The files are on Hugging Face in the Sam2x/SeFi-Image-5B-turbo-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.