gpt2 needs about 2.4 GB of memory at F32 (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.7 GB (F32) to 6.6 GB (F32).
gpt2 is a 163M-parameter Gpt model in GGUF format, quantized by hikettei. Its trained context length is 1K tokens. The repository has 4 quant files, from 0.7 GB (F32) to 6.6 GB (F32).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F32 | 0.7 GB | 1.2 GB | Fits | Get file → | |
| F32 | 1.6 GB | 2.2 GB | Fits | Get file → | |
| F32 | 3.4 GB | 3.9 GB | Fits | Get file → | |
| F32 | 6.6 GB | 7.1 GB | Fits | Get file → |
What GPU do you need for gpt2?
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 F32 (1.6 GB file, about 2.4 GB in use).
- 6 GB VRAM: the best quant that fits is F32 (3.4 GB file, about 4.2 GB in use).
- 8 GB VRAM: the best quant that fits is F32 (6.6 GB file, about 7.4 GB in use).
Which gpt2 quant should you choose?
F32 (1.6 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is F32 at 0.7 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gpt2
How much VRAM does gpt2 need?
About 2.4 GB at F32 with an 8K context window. That is the 1.6 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 gpt2 on an 8 GB GPU?
Yes, with F32: the 6.6 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gpt2 GGUF?
It depends on the quant: F32 is 0.7 GB, F32 is 1.6 GB, F32 is 3.4 GB, F32 is 6.6 GB.
What context length does gpt2 support?
The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 1K.
Where can I download gpt2 GGUF?
The files are on Hugging Face in the hikettei/gpt2-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 gpt2 use?
Hugging Face lists the license as unknown. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.