GP

gpt2 Q8 0

GptGGUF by igorbkzUpdated 2024-05-04
Download on Hugging Face
Parameters163M
Context1K
Layers12
Architecturegpt2
Smallest quant0.2 GB
Quick answer

gpt2 Q8 0 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.

gpt2 Q8 0 is a 163M-parameter Gpt model in GGUF format, quantized by igorbkz. Its trained context length is 1K tokens. The repository has 1 quant file, from 0.2 GB (Q8_0) to 0.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.2 GB 0.7 GB
Fits Get file →

What GPU do you need for gpt2 Q8 0?

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_0 (0.2 GB file, about 1.0 GB in use).

Which gpt2 Q8 0 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.

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 byigorbkz
FamilyGpt
Licensemit
Downloads (HF)233
Last updated2024-05-04

Frequently asked questions about gpt2 Q8 0

How much VRAM does gpt2 Q8 0 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 gpt2 Q8 0 on an 8 GB GPU?

Yes, with Q8_0: the 0.2 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gpt2 Q8 0 GGUF?

It depends on the quant: Q8_0 is 0.2 GB.

What context length does gpt2 Q8 0 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 Q8 0 GGUF?

The files are on Hugging Face in the igorbkz/gpt2-Q8_0-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 Q8 0 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 igorbkz

All by igorbkz →

More Gpt models

All Gpt →

Other tiny models

All tiny models →