Apertus GGUF models
131 GGUF models in the Apertus family, quantized by 32 uploaders. Sizes run from 438M to 70.6B parameters. The longest trained context is 256K tokens.
About the Apertus GGUF models
Apertus is represented on ggufmodels.com by 131 GGUF models, quantized by 32 uploaders on Hugging Face. The most downloaded are Apertus-8B-Instruct-2509, Apertus-70B-Instruct-2509 and Apertus 70B Instruct 2509 Abliterated. Parameter counts run from 438M to 70.6B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Apertus model is between 0.3 to 43.7 GB, which is the quant most people start with. Most files come from mradermacher (59), NonMiFrega (14) and Colby (6). The quants you will meet most often are Q4_K_M (103), Q5_K_M (85), Q6_K (72) and Q3_K_M (69), where the number is how many models offer that quant.
Frequently asked questions
Which Apertus GGUF should I download?
The most downloaded Apertus GGUF here is Apertus-8B-Instruct-2509. 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 Apertus model need?
Q4_K_M files of Apertus models on this site range from 0.3 to 43.7 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 Apertus GGUF files come from?
The most common quantizers here are mradermacher, NonMiFrega and Colby. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.