Ornith GGUF models
416 GGUF models in the Ornith family, quantized by 232 uploaders. Sizes run from 1M to 417B parameters. The longest trained context is 1024K tokens.
About the Ornith GGUF models
Ornith is represented on ggufmodels.com by 416 GGUF models, quantized by 232 uploaders on Hugging Face. The most downloaded are Ornith-1.5-9B, Ornith-1.5-35B and Tiel Coder 35B A3B GGUF MTP. Parameter counts run from 1M to 417B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Ornith model is between 0.5 to 264.4 GB, which is the quant most people start with. Most files come from mradermacher (50), kingjones777 (14) and bartowski (7). The quants you will meet most often are Q4_K_M (217), Q8_0 (195), Q6_K (168) and Q5_K_M (165), where the number is how many models offer that quant.
Frequently asked questions
Which Ornith GGUF should I download?
The most downloaded Ornith GGUF here is Ornith-1.5-9B. 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 Ornith model need?
Q4_K_M files of Ornith models on this site range from 0.5 to 264.4 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 Ornith GGUF files come from?
The most common quantizers here are mradermacher, kingjones777 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.