DI

distilgpt2

DistilgptGGUF by QuantFactoryUpdated 2024-09-01
Download on Hugging Face
Parameters121M
Context1K
Layers6
Architecturegpt2
Smallest quant0.1 GB
Quick answer

distilgpt2 needs about 0.7 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.1 GB (Q2_K) to 0.1 GB (Q8_0).

DistilGPT2: a lightweight 82‑million‑parameter text generation model

DistilGPT2 is a distilled version of GPT‑2 with 82 million parameters. It is trained on English text and can generate coherent passages. The model is available in multiple GGUF quantizations.

Good at

  • Fast inference
  • Low memory footprint
  • English text generation

Limits

  • No vision support
  • Limited to 1024‑token context
  • Apache‑2.0 license

Best for

  • Quick prototyping
  • Embedded devices
  • Low‑resource inference

Who it’s for. Developers needing a small, fast language model for English text generation. Researchers and hobbyists who require a lightweight alternative to GPT‑2.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.6 GB
Fits Get file →
Q3_K_S0.1 GB 0.6 GB
Fits Get file →
Q3_K_M0.1 GB 0.6 GB
Fits Get file →
Q3_K_L0.1 GB 0.6 GB
Fits Get file →
Q4_00.1 GB 0.6 GB
Fits Get file →
Q4_K_S0.1 GB 0.6 GB
Fits Get file →
Q4_K_M0.1 GB 0.6 GB
Fits Get file →
Q4_10.1 GB 0.6 GB
Fits Get file →
Q5_00.1 GB 0.6 GB
Fits Get file →
Q5_K_S0.1 GB 0.6 GB
Fits Get file →
Q5_K_M0.1 GB 0.6 GB
Fits Get file →
Q5_10.1 GB 0.6 GB
Fits Get file →
Q6_K0.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.7 GB
Fits Get file →

For 8 GB VRAM, Q2_K or Q3_K_S are suitable, each 0.07 GB file and ~0.7 GB memory at 8k context. If more precision is needed, Q4_K_M (0.08 GB, ~0.7 GB) can be used. Larger quantizations like Q6_K or Q8_0 consume more memory and are unnecessary for most use cases.

What GPU do you need for distilgpt2?

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 (0.1 GB file, about 0.8 GB in use).

Which distilgpt2 quant should you choose?

Q4_K_M is the usual starting point for distilgpt2: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.1 GB, about 1.6 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 0.1 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
Parameters121M
Layers6
Trained context1,024 tokens
KV cache (fp16)18 KB per token

Source

Quantized byQuantFactory
FamilyDistilgpt
Licenseapache-2.0
Downloads (HF)1,594
Last updated2024-09-01

Frequently asked questions about distilgpt2

How much VRAM does distilgpt2 need?

About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.1 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 distilgpt2 on an 8 GB GPU?

Yes, with Q8_0: the 0.1 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of distilgpt2 GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_0 is 0.1 GB, Q4_K_S is 0.1 GB and 8 more.

What context length does distilgpt2 support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 1K.

Where can I download distilgpt2 GGUF?

The files are on Hugging Face in the QuantFactory/distilgpt2-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 distilgpt2 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run distilgpt2 on 8 GB VRAM?

Yes. The Q2_K and Q3_K_S quantizations use only about 0.7 GB of VRAM at 8k context, well within 8 GB.

Does distilgpt2 support multiple languages?

No. The model is trained only on English text.

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Distilgpt models

All Distilgpt →

Other tiny models

All tiny models →