GP

Gpt2 Medium

GptGGUF by antosteUpdated 2024-08-20
Download on Hugging Face
Parameters406M
Context1K
Layers24
Architecturegpt2
Smallest quant0.2 GB
Quick answer

Gpt2 Medium needs about 1.6 GB of memory at Q4_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Gpt2 Medium is a 406M-parameter Gpt model in GGUF format, quantized by antoste. Its trained context length is 1K tokens. The repository has 1 quant file, from 0.2 GB (Q4_0) to 0.2 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.2 GB 0.8 GB
Fits Get file →

What GPU do you need for Gpt2 Medium?

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 Q4_0 (0.2 GB file, about 1.6 GB in use).

Which Gpt2 Medium quant should you choose?

Q4_0 (0.2 GB) is the middle option in this repository. 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
Parameters406M
Layers24
Trained context1,024 tokens
KV cache (fp16)96 KB per token

Source

Quantized byantoste
FamilyGpt
Licensemit
Downloads (HF)44
Last updated2024-08-20

Frequently asked questions about Gpt2 Medium

How much VRAM does Gpt2 Medium need?

About 1.6 GB at Q4_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 Medium on an 8 GB GPU?

Yes, with Q4_0: the 0.2 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gpt2 Medium GGUF?

It depends on the quant: Q4_0 is 0.2 GB.

What context length does Gpt2 Medium support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 1K.

Where can I download Gpt2 Medium GGUF?

The files are on Hugging Face in the antoste/gpt2-medium-Q4_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 Medium 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.

Other GGUFs of gpt2-medium

Similar models

Browse all →

More from antoste

All by antoste →

More Gpt models

All Gpt →

Other tiny models

All tiny models →