Captain GGUF models
101 GGUF models in the Captain family, quantized by 15 uploaders. Sizes run from 3M to 32.3B parameters. The longest trained context is 1000K tokens.
About the Captain GGUF models
Captain is represented on ggufmodels.com by 101 GGUF models, quantized by 15 uploaders on Hugging Face. The most downloaded are Captain Eris Twighlight V0.420 12B, Captain Eris Violet V0.420 12B GGUF ARM Imatrix and Captain Eris Diogenes Twilight V0.420 12B GGUF ARM Imatrix. Parameter counts run from 3M to 32.3B, and the longest trained context window is 1000K tokens.
A Q4_K_M file of a Captain model is between 3.1 to 19.8 GB, which is the quant most people start with. Most files come from mradermacher (65), bartowski (6) and MaziyarPanahi (5). The quants you will meet most often are Q6_K (89), Q5_K_M (88), Q5_K_S (87) and Q4_K_M (86), where the number is how many models offer that quant.
Frequently asked questions
Which Captain GGUF should I download?
The most downloaded Captain GGUF here is Captain Eris Twighlight V0.420 12B. 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 Captain model need?
Q4_K_M files of Captain models on this site range from 3.1 to 19.8 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 Captain GGUF files come from?
The most common quantizers here are mradermacher, bartowski and MaziyarPanahi. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.