15313 needs about 11.5 GB of memory at Q6_K_XL (a 10.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 2.8 GB (Q8_K_XL) to 13.6 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
15313 is a 11.8B-parameter model in GGUF format, quantized by 08443u0. Its trained context length is 256K tokens. The repository has 11 quant files, from 2.8 GB (Q8_K_XL) to 13.6 GB (Q8_K_XL).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_K_XL | 2.8 GB | 3.7 GB | Fits | Get file → | |
| Q8_1 | 8.1 GB | 9.0 GB | Too big | Get file → | |
| Q8_0 | 8.5 GB | 9.4 GB | Too big | Get file → | |
| Q8_K_XL | 8.7 GB | 9.6 GB | Too big | Get file → | |
| Q8_K_XL | 8.7 GB | 9.6 GB | Too big | Get file → | |
| Q6_K_XL | 10.6 GB | 11.5 GB | Too big | Get file → | |
| Q6_K_XL | 10.7 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_XL | 12.9 GB | 13.8 GB | Too big | Get file → | |
| Q8_1 | 13.0 GB | 13.9 GB | Too big | Get file → | |
| Q3_K_S | 13.2 GB | 14.1 GB | Too big | Get file → | |
| Q8_K_XL | 13.6 GB | 14.5 GB | Too big | Get file → |
What GPU do you need for 15313?
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: the best quant that fits is Q8_K_XL (2.8 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_K_XL (2.8 GB file, about 3.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_K_XL (2.8 GB file, about 3.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K_XL (10.7 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_K_XL (13.6 GB file, about 14.5 GB in use).
Which 15313 quant should you choose?
Q6_K_XL (10.6 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 Q8_K_XL at 2.8 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about 15313
How much VRAM does 15313 need?
About 11.5 GB at Q6_K_XL with an 8K context window. That is the 10.6 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 15313 on an 8 GB GPU?
Yes, with Q8_K_XL: the 2.8 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of 15313 GGUF?
It depends on the quant: Q8_K_XL is 2.8 GB, Q8_1 is 8.1 GB, Q8_0 is 8.5 GB, Q8_K_XL is 8.7 GB, Q8_K_XL is 8.7 GB, Q6_K_XL is 10.6 GB and 5 more.
What context length does 15313 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download 15313 GGUF?
The files are on Hugging Face in the 08443u0/15313 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does 15313 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.