Sailor GGUF models
126 GGUF models in the Sailor family, quantized by 24 uploaders. Sizes run from 620M to 19.2B parameters. The longest trained context is 128K tokens.
About the Sailor GGUF models
Sailor is represented on ggufmodels.com by 126 GGUF models, quantized by 24 uploaders on Hugging Face. The most downloaded are Sailor2 8B Chat, Sailor2 20B Chat and Sailor-0.5B. Parameter counts run from 620M to 19.2B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Sailor model is between 0.4 to 13.4 GB, which is the quant most people start with. Most files come from mradermacher (52), itlwas (15) and RichardErkhov (11). The quants you will meet most often are Q4_K_M (110), Q2_K (100), Q3_K_M (99) and Q5_K_M (92), where the number is how many models offer that quant.
Frequently asked questions
Which Sailor GGUF should I download?
The most downloaded Sailor GGUF here is Sailor2 8B Chat. 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 Sailor model need?
Q4_K_M files of Sailor models on this site range from 0.4 to 13.4 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 Sailor 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.