Qwythos GGUF models
125 GGUF models in the Qwythos family, quantized by 100 uploaders. Sizes run from 1M to 71.8B parameters. The longest trained context is 1024K tokens.
About the Qwythos GGUF models
Qwythos is represented on ggufmodels.com by 125 GGUF models, quantized by 100 uploaders on Hugging Face. The most downloaded are Qwythos-9B-v2, Qwythos 9B Claude Mythos 5 1M and Qwythos-27B. Parameter counts run from 1M to 71.8B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Qwythos model is between 5.6 to 43.7 GB, which is the quant most people start with. Most files come from mradermacher (11), empero-ai (3) and developerjeremylive (3). The quants you will meet most often are Q5_K_M (102), Q4_K_M (102), Q8_0 (100) and Q6_K (98), where the number is how many models offer that quant.
Frequently asked questions
Which Qwythos GGUF should I download?
The most downloaded Qwythos GGUF here is Qwythos-9B-v2. 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 Qwythos model need?
Q4_K_M files of Qwythos models on this site range from 5.6 to 43.7 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 Qwythos GGUF files come from?
The most common quantizers here are mradermacher, empero-ai and developerjeremylive. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.