GP

gpt2-xl

GptGGUF by ZeroWwUpdated 2024-07-13
Download on Hugging Face
Parameters1.64B
Context1K
Layers48
Architecturegpt2
Smallest quant1.6 GB
Quick answer

gpt2-xl needs about 4.8 GB of memory at Q6_K (a 1.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 1.6 GB (Q5_K) to 3.3 GB (F16).

gpt2-xl is a 1.64B-parameter Gpt model in GGUF format, quantized by ZeroWw. Its trained context length is 1K tokens. The repository has 5 quant files, from 1.6 GB (Q5_K) to 3.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K1.6 GB 2.4 GB
Fits Get file →
—1.7 GB 2.6 GB
Fits Get file →
Q6_K1.8 GB 2.6 GB
Fits Get file →
Q8_01.9 GB 2.7 GB
Fits Get file →
F163.3 GB 4.1 GB
Fits Get file →

What GPU do you need for gpt2-xl?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q8_0 (1.9 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (3.3 GB file, about 6.3 GB in use).

Which gpt2-xl quant should you choose?

Q6_K (1.8 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 Q5_K at 1.6 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt2
Parameters1.64B
Layers48
Trained context1,024 tokens
KV cache (fp16)300 KB per token

Source

Quantized byZeroWw
FamilyGpt
Licensemit
Downloads (HF)44
Last updated2024-07-13

Frequently asked questions about gpt2-xl

How much VRAM does gpt2-xl need?

About 4.8 GB at Q6_K with an 8K context window. That is the 1.8 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-xl on an 8 GB GPU?

Yes, with F16: the 3.3 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gpt2-xl GGUF?

It depends on the quant: Q5_K is 1.6 GB, file is 1.7 GB, Q6_K is 1.8 GB, Q8_0 is 1.9 GB, F16 is 3.3 GB.

What context length does gpt2-xl support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 2.5 GB at 8K and 0.3 GB at 1K.

Where can I download gpt2-xl GGUF?

The files are on Hugging Face in the ZeroWw/gpt2-xl-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-xl 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 ZeroWw

All by ZeroWw →

More Gpt models

All Gpt →

Other tiny models

All tiny models →