GP

GPT 2

GptGGUF by ddh0Updated 2024-07-31
Download on Hugging Face
Parameters163M
Context1K
Layers12
Architecturegpt2
Smallest quant0.1 GB
Quick answer

GPT 2 needs about 1.0 GB of memory at Q8_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (Q4_K_S) to 0.7 GB (F32).

GPT 2 is a 163M-parameter Gpt model in GGUF format, quantized by ddh0. Its trained context length is 1K tokens. The repository has 3 quant files, from 0.1 GB (Q4_K_S) to 0.7 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S0.1 GB 0.7 GB
Fits Get file →
Q8_00.2 GB 0.7 GB
Fits Get file →
F320.7 GB 1.2 GB
Fits Get file →

What GPU do you need for GPT 2?

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 (0.7 GB file, about 1.5 GB in use).

Which GPT 2 quant should you choose?

Q8_0 (0.2 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 Q4_K_S at 0.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt2
Parameters163M
Layers12
Trained context1,024 tokens
KV cache (fp16)36 KB per token

Source

Quantized byddh0
FamilyGpt
Repositoryddh0/GPT-2-GGUF
Licensemit
Downloads (HF)74
Last updated2024-07-31

Frequently asked questions about GPT 2

How much VRAM does GPT 2 need?

About 1.0 GB at Q8_0 with an 8K context window. That is the 0.2 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 GPT 2 on an 8 GB GPU?

Yes, with F32: the 0.7 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GPT 2 GGUF?

It depends on the quant: Q4_K_S is 0.1 GB, Q8_0 is 0.2 GB, F32 is 0.7 GB.

What context length does GPT 2 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 GPT 2 GGUF?

The files are on Hugging Face in the ddh0/GPT-2-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 GPT 2 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.

Similar models

Browse all →

More from ddh0

All by ddh0 →

More Gpt models

All Gpt →

Other tiny models

All tiny models →