Ice GGUF models
180 GGUF models in the Ice family, quantized by 33 uploaders. Sizes run from 1.24B to 13B parameters. The longest trained context is 128K tokens.
About the Ice GGUF models
Ice is represented on ggufmodels.com by 180 GGUF models, quantized by 33 uploaders on Hugging Face. The most downloaded are darkps ice AI, ice AI i1 and Ice0.17 03.10 RP i1. Parameter counts run from 1.24B to 13B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Ice model is between 4.4 to 7.9 GB, which is the quant most people start with. Most files come from mradermacher (142), PAUL1122 (4) and youngcho (2). The quants you will meet most often are Q6_K (144), Q5_K_S (144), Q5_K_M (144) and Q4_K_S (144), where the number is how many models offer that quant.
Frequently asked questions
Which Ice GGUF should I download?
The most downloaded Ice GGUF here is darkps ice AI. 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 Ice model need?
Q4_K_M files of Ice models on this site range from 4.4 to 7.9 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 Ice GGUF files come from?
The most common quantizers here are mradermacher, PAUL1122 and youngcho. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.