Hermes GGUF models
149 GGUF models in the Hermes family, quantized by 49 uploaders. Sizes run from 19M to 406B parameters. The longest trained context is 512K tokens.
About the Hermes GGUF models
Hermes is represented on ggufmodels.com by 149 GGUF models, quantized by 49 uploaders on Hugging Face. The most downloaded are Hermes 4 14B, Hermes-4-70B and NousResearch_Hermes 4 70B. Parameter counts run from 19M to 406B, and the longest trained context window is 512K tokens.
A Q4_K_M file of a Hermes model is between 0.8 to 243.1 GB, which is the quant most people start with. Most files come from mradermacher (74), harkov000 (5) and danrichard6tyt (5). The quants you will meet most often are Q4_K_M (115), Q5_K_M (102), Q2_K (92) and Q3_K_M (90), where the number is how many models offer that quant.
Frequently asked questions
Which Hermes GGUF should I download?
The most downloaded Hermes GGUF here is Hermes 4 14B. 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 Hermes model need?
Q4_K_M files of Hermes models on this site range from 0.8 to 243.1 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 Hermes GGUF files come from?
The most common quantizers here are mradermacher, harkov000 and danrichard6tyt. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.