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.
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.