OP

openai_GPT 2 XL 1.5B

OpenaiGGUF by LyraNovaHeartUpdated 2024-09-05
Download on Hugging Face
Parameters1.64B
Context1K
Layers48
Architecturegpt2
Smallest quant1.2 GB
Quick answer

openai_GPT 2 XL 1.5B 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 7 quants, from 1.2 GB (Q4_K_M) to 6.6 GB (F32).

openai_GPT 2 XL 1.5B is a 1.64B-parameter Openai model in GGUF format, quantized by LyraNovaHeart. Its trained context length is 1K tokens. The repository has 7 quant files, from 1.2 GB (Q4_K_M) to 6.6 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.2 GB 2.0 GB
Fits Get file →
Q5_K_S1.2 GB 2.0 GB
Fits Get file →
Q5_K_M1.4 GB 2.2 GB
Fits Get file →
Q6_K1.6 GB 2.4 GB
Fits Get file →
Q8_01.7 GB 2.6 GB
Fits Get file →
—3.3 GB 4.1 GB
Fits Get file →
F326.6 GB 7.4 GB
Tight Get file →

What GPU do you need for openai_GPT 2 XL 1.5B?

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 (1.7 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).
  • 12 GB VRAM: the best quant that fits is F32 (6.6 GB file, about 9.6 GB in use).

Which openai_GPT 2 XL 1.5B quant should you choose?

Q4_K_M is the usual starting point for openai_GPT 2 XL 1.5B: 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.

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 byLyraNovaHeart
FamilyOpenai
Licensemit
Downloads (HF)117
Last updated2024-09-05

Frequently asked questions about openai_GPT 2 XL 1.5B

How much VRAM does openai_GPT 2 XL 1.5B 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 openai_GPT 2 XL 1.5B 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 openai_GPT 2 XL 1.5B GGUF?

It depends on the quant: Q4_K_M is 1.2 GB, Q5_K_S is 1.2 GB, Q5_K_M is 1.4 GB, Q6_K is 1.6 GB, Q8_0 is 1.7 GB, file is 3.3 GB and 1 more.

What context length does openai_GPT 2 XL 1.5B 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 openai_GPT 2 XL 1.5B GGUF?

The files are on Hugging Face in the LyraNovaHeart/GPT-2-XL-1.5b-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 openai_GPT 2 XL 1.5B 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 LyraNovaHeart

All by LyraNovaHeart →

More Openai models

All Openai →

Other tiny models

All tiny models →