Pantheon GGUF models
87 GGUF models in the Pantheon family, quantized by 20 uploaders. Sizes run from 1.17B to 39.8B parameters. The longest trained context is 1000K tokens.
About the Pantheon GGUF models
Pantheon is represented on ggufmodels.com by 87 GGUF models, quantized by 20 uploaders on Hugging Face. The most downloaded are Pantheon Reasoning 26B A4B 1.1 V2, Pantheon Reasoning 26B A4B 1.1 V2 and Pantheon Reasoning 27B. Parameter counts run from 1.17B to 39.8B, and the longest trained context window is 1000K tokens.
A Q4_K_M file of a Pantheon model is between 0.7 to 23.8 GB, which is the quant most people start with. Most files come from mradermacher (38), roleplaiapp (14) and bartowski (11). The quants you will meet most often are Q4_K_M (66), Q3_K_M (64), Q6_K (63) and Q5_K_S (63), where the number is how many models offer that quant.
Frequently asked questions
Which Pantheon GGUF should I download?
The most downloaded Pantheon GGUF here is Pantheon Reasoning 26B A4B 1.1 V2. 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 Pantheon model need?
Q4_K_M files of Pantheon models on this site range from 0.7 to 23.8 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 Pantheon GGUF files come from?
The most common quantizers here are mradermacher, roleplaiapp and bartowski. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.