Korat needs about 2.4 GB of memory at Q8_0 (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.3 GB (Q6_K) to 3.1 GB (F16).
Korat is a 1.53B-parameter Korat model in GGUF format, quantized by Gonanf. Its trained context length is 1024K tokens. The repository has 3 quant files, from 1.3 GB (Q6_K) to 3.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.4 GB | Fits | Get file → | |
| F16 | 3.1 GB | 3.9 GB | Fits | Get file → |
What GPU do you need for Korat?
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 (3.1 GB file, about 3.9 GB in use).
Which Korat quant should you choose?
Q8_0 (1.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q6_K at 1.3 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 Korat
How much VRAM does Korat need?
About 2.4 GB at Q8_0 with an 8K context window. That is the 1.7 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 Korat on an 8 GB GPU?
Yes, with F16: the 3.1 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Korat GGUF?
It depends on the quant: Q6_K is 1.3 GB, Q8_0 is 1.7 GB, F16 is 3.1 GB.
What context length does Korat support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download Korat GGUF?
The files are on Hugging Face in the Gonanf/Korat-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.