Dialogpt GGUF models
192 GGUF models in the Dialogpt family, quantized by 11 uploaders. Sizes run from 121M to 6.74B parameters. The longest trained context is 4K tokens.
About the Dialogpt GGUF models
Dialogpt is represented on ggufmodels.com by 192 GGUF models, quantized by 11 uploaders on Hugging Face. The most downloaded are DialoGPT MedDialog large, DialoGPT small crybaby and DialoGPT medium Loki. Parameter counts run from 121M to 6.74B, and the longest trained context window is 4K tokens.
A Q4_K_M file of a Dialogpt model is between 0.1 to 0.5 GB, which is the quant most people start with. Most files come from mradermacher (148), devparagiri (16) and roleplaiapp (12). The quants you will meet most often are Q2_K (162), Q4_K_M (161), Q3_K_M (161) and Q6_K (159), where the number is how many models offer that quant.
Frequently asked questions
Which Dialogpt GGUF should I download?
The most downloaded Dialogpt GGUF here is DialoGPT MedDialog large. 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 Dialogpt model need?
Q4_K_M files of Dialogpt models on this site range from 0.1 to 0.5 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 Dialogpt GGUF files come from?
The most common quantizers here are mradermacher, devparagiri and roleplaiapp. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.