Apollo GGUF models
105 GGUF models in the Apollo family, quantized by 26 uploaders. Sizes run from 14M to 70.6B parameters. The longest trained context is 256K tokens.
About the Apollo GGUF models
Apollo is represented on ggufmodels.com by 105 GGUF models, quantized by 26 uploaders on Hugging Face. The most downloaded are Apollo Astralis 4b, Apollo 1 8B and Apollo V0.1 4B Thinking. Parameter counts run from 14M to 70.6B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Apollo model is between 0.3 to 42.5 GB, which is the quant most people start with. Most files come from mradermacher (55), itlwas (5) and RichardErkhov (5). The quants you will meet most often are Q4_K_M (86), Q2_K (77), Q5_K_M (75) and Q5_K_S (72), where the number is how many models offer that quant.
Frequently asked questions
Which Apollo GGUF should I download?
The most downloaded Apollo GGUF here is Apollo Astralis 4b. 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 Apollo model need?
Q4_K_M files of Apollo models on this site range from 0.3 to 42.5 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 Apollo GGUF files come from?
The most common quantizers here are mradermacher, itlwas and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.