Orca GGUF models
161 GGUF models in the Orca family, quantized by 36 uploaders. Sizes run from 1.1B to 72.7B parameters. The longest trained context is 256K tokens.
About the Orca GGUF models
Orca is represented on ggufmodels.com by 161 GGUF models, quantized by 36 uploaders on Hugging Face. The most downloaded are Orca 2 13b, Orca 2 7B and Orca 2 13B. Parameter counts run from 1.1B to 72.7B, and the longest trained context window is 256K tokens.
A Q4_K_M file of a Orca model is between 0.7 to 47.4 GB, which is the quant most people start with. Most files come from mradermacher (90), tensorblock (15) and RichardErkhov (10). The quants you will meet most often are Q2_K (132), Q4_K_M (122), Q3_K_M (121) and Q5_K_M (118), where the number is how many models offer that quant.
Frequently asked questions
Which Orca GGUF should I download?
The most downloaded Orca GGUF here is Orca 2 13b. 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 Orca model need?
Q4_K_M files of Orca models on this site range from 0.7 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 Orca GGUF files come from?
The most common quantizers here are mradermacher, tensorblock 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.