Arcee GGUF models
81 GGUF models in the Arcee family, quantized by 26 uploaders. Sizes run from 450M to 72.7B parameters. The longest trained context is 128K tokens.
About the Arcee GGUF models
Arcee is represented on ggufmodels.com by 81 GGUF models, quantized by 26 uploaders on Hugging Face. The most downloaded are Arcee-Agent, Arcee Nova and arcee ai Arcee Maestro 7B Preview. Parameter counts run from 450M to 72.7B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Arcee model is between 1.0 to 47.4 GB, which is the quant most people start with. Most files come from mradermacher (23), arcee-ai (8) and bartowski (6). The quants you will meet most often are Q2_K (62), Q4_K_M (61), Q6_K (57) and Q5_K_M (57), where the number is how many models offer that quant.
Frequently asked questions
Which Arcee GGUF should I download?
The most downloaded Arcee GGUF here is Arcee-Agent. 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 Arcee model need?
Q4_K_M files of Arcee models on this site range from 1.0 to 47.4 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 Arcee GGUF files come from?
The most common quantizers here are mradermacher, arcee-ai 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.