GP

Gpt2 Xl

GptGGUF by mardakaniUpdated 2024-08-16
Download on Hugging Face
Parameters1.64B
Context1K
Layers48
Architecturegpt2
Smallest quant0.9 GB
Quick answer

Gpt2 Xl needs about 4.2 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 0.9 GB (Q2_K) to 3.3 GB.

Gpt2 Xl is a 1.64B-parameter Gpt model in GGUF format, quantized by mardakani. Its trained context length is 1K tokens. The repository has 4 quant files, from 0.9 GB (Q2_K) to 3.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.9 GB 1.7 GB
Fits Get file →
Q4_K_M1.2 GB 2.0 GB
Fits Get file →
Q8_01.7 GB 2.6 GB
Fits Get file →
—3.3 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: the best quant that fits is Q2_K (0.9 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (1.7 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (3.3 GB file, about 6.3 GB in use).

Which Gpt2 Xl quant should you choose?

Q4_K_M is the usual starting point for Gpt2 Xl: it balances file size and quality well. Here it is a 1.2 GB file.

The Q8_0 file is 1.7 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 bymardakani
FamilyGpt
Licensemit
Downloads (HF)4
Last updated2024-08-16

Frequently asked questions about Gpt2 Xl

How much VRAM does Gpt2 Xl need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.2 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 Xl on an 8 GB GPU?

Yes, with the smaller files: 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: Q2_K is 0.9 GB, Q4_K_M is 1.2 GB, Q8_0 is 1.7 GB, file 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 mardakani/gpt2-xl 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 mardakani

All by mardakani →

More Gpt models

All Gpt →

Other tiny models

All tiny models →