TURNA needs about 1.4 GB of memory at Q5_0 (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.4 GB to 4.6 GB (F32).
TURNA is a 1.14B-parameter Turna model in GGUF format, quantized by helizac. The repository has 14 quant files, from 0.4 GB to 4.6 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.4 GB | 0.9 GB | Fits | Get file → | |
| — | 0.5 GB | 1.1 GB | Fits | Get file → | |
| — | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q4_0 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q4_1 | 0.7 GB | 1.3 GB | Fits | Get file → | |
| — | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q5_0 | 0.8 GB | 1.4 GB | Fits | Get file → | |
| Q5_1 | 0.9 GB | 1.5 GB | Fits | Get file → | |
| — | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| Q8_1 | 1.3 GB | 1.9 GB | Fits | Get file → | |
| — | 1.3 GB | 2.0 GB | Fits | Get file → | |
| F16 | 2.3 GB | 3.1 GB | Fits | Get file → | |
| F32 | 4.6 GB | 5.6 GB | Fits | Get file → |
What GPU do you need for TURNA?
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 (2.3 GB file, about 3.1 GB in use).
- 6 GB VRAM: the best quant that fits is F32 (4.6 GB file, about 5.6 GB in use).
Which TURNA quant should you choose?
Q5_0 (0.8 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 the first one in the table at 0.4 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 TURNA
How much VRAM does TURNA need?
About 1.4 GB at Q5_0 with an 8K context window. That is the 0.8 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 TURNA on an 8 GB GPU?
Yes, with F32: the 4.6 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of TURNA GGUF?
It depends on the quant: file is 0.4 GB, file is 0.5 GB, file is 0.6 GB, Q4_0 is 0.6 GB, Q4_1 is 0.7 GB, file is 0.8 GB and 8 more.
Where can I download TURNA GGUF?
The files are on Hugging Face in the helizac/TURNA_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 TURNA use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.