Orpheus GGUF models
187 GGUF models in the Orpheus family, quantized by 76 uploaders. Sizes run from 97M to 8.03B parameters. The longest trained context is 128K tokens.
About the Orpheus GGUF models
Orpheus is represented on ggufmodels.com by 187 GGUF models, quantized by 76 uploaders on Hugging Face. The most downloaded are Orpheus-3B-0.1-Ft, orpheus 3b 0.1 ft Q4 K M and Orpheus 3b FT Q8 0. Parameter counts run from 97M to 8.03B, and the longest trained context window is 128K tokens.
A Q4_K_M file of a Orpheus model is between 0.4 to 4.9 GB, which is the quant most people start with. Most files come from mradermacher (54), lex-au (14) and tingting (11). The quants you will meet most often are Q8_0 (126), Q4_K_M (122), Q5_K_M (87) and F16 (75), where the number is how many models offer that quant.
Frequently asked questions
Which Orpheus GGUF should I download?
The most downloaded Orpheus GGUF here is Orpheus-3B-0.1-Ft. 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 Orpheus model need?
Q4_K_M files of Orpheus models on this site range from 0.4 to 4.9 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 Orpheus GGUF files come from?
The most common quantizers here are mradermacher, lex-au and tingting. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.