Gpt GGUF models
724 GGUF models in the Gpt family, quantized by 143 uploaders. Sizes run from 2M to 117B parameters. The longest trained context is 256K tokens.
About the Gpt GGUF models
Gpt is represented on ggufmodels.com by 724 GGUF models, quantized by 143 uploaders on Hugging Face. The most downloaded are Gpt2 Medium, gpt2 GGUF smashed and gpt2 i1. Parameter counts run from 2M to 117B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Gpt model is between 0.0 to 87.9 GB, which is the quant most people start with. Most files come from mradermacher (286), RichardErkhov (153) and tensorblock (65). The quants you will meet most often are Q2_K (537), Q4_K_M (534), Q3_K_M (488) and Q5_K_M (487), where the number is how many models offer that quant.
Frequently asked questions
Which Gpt GGUF should I download?
The most downloaded Gpt GGUF here is Gpt2 Medium. 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 Gpt model need?
Q4_K_M files of Gpt models on this site range from 0.0 to 87.9 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 Gpt 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.