mGPT 13B needs about 11.6 GB of memory at Q6_K (a 9.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 9.9 GB (Q6_K) to 10.1 GB (Q5_K_M).
mGPT 13B is a 13.6B-parameter Mgpt model in GGUF format, quantized by Sosnitskij. Its trained context length is 2K tokens. The repository has 2 quant files, from 9.9 GB (Q6_K) to 10.1 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 9.9 GB | 10.7 GB | Too big | Get file → | |
| Q5_K_M | 10.1 GB | 10.9 GB | Too big | Get file → |
What GPU do you need for mGPT 13B?
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: the best quant that fits is Q5_K_M (10.1 GB file, about 11.9 GB in use).
Which mGPT 13B quant should you choose?
Q6_K (9.9 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about mGPT 13B
How much VRAM does mGPT 13B need?
About 11.6 GB at Q6_K with an 8K context window. That is the 9.9 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 mGPT 13B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of mGPT 13B GGUF?
It depends on the quant: Q6_K is 9.9 GB, Q5_K_M is 10.1 GB.
What context length does mGPT 13B support?
The GGUF header lists a trained context length of 2,048 tokens (2K).
Where can I download mGPT 13B GGUF?
The files are on Hugging Face in the Sosnitskij/mGPT-13B-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 mGPT 13B use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.