Distilgpt GGUF models

88 GGUF models in the Distilgpt family, quantized by 13 uploaders. Sizes run from 82M to 3.21B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
DI
distilgpt2
Distilgpt · QuantFactory
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
distilgpt2
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · QuantFactory
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · QuantFactory
Params121M
Context1K
Q4_K_M0.1 GB
Coding
DI
Distilgpt2 Tiny Conversational
Distilgpt · mradermacher
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
distilgpt2-tiny-conversational
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
Coding
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
DistilGPT2-TinyStories
Distilgpt · mradermacher
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
distilgpt2-stable-diffusion
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2 Tiny Conversational
Distilgpt · mradermacher
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2 Emailgen V2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
distilgpt2-HC3
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · mradermacher
Params82M
Context1K
Q4_K_M0.1 GB
GGUF
DI
Distilgpt2
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
GGUF

About the Distilgpt GGUF models

Distilgpt is represented on ggufmodels.com by 88 GGUF models, quantized by 13 uploaders on Hugging Face. The most downloaded are distilgpt2, distilgpt2 and Distilgpt2. Parameter counts run from 82M to 3.21B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Distilgpt model is between 0.1 to 0.1 GB, which is the quant most people start with. Most files come from mradermacher (40), RichardErkhov (30) and tensorblock (5). The quants you will meet most often are Q2_K (79), Q4_K_M (77), Q3_K_M (77) and Q4_K_S (74), where the number is how many models offer that quant.

Frequently asked questions

Which Distilgpt GGUF should I download?

The most downloaded Distilgpt GGUF here is distilgpt2. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Distilgpt model need?

Q4_K_M files of Distilgpt models on this site range from 0.1 to 0.1 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Distilgpt GGUF files come from?

The most common quantizers here are mradermacher, RichardErkhov and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing