Seed GGUF models
111 GGUF models in the Seed family, quantized by 49 uploaders. Sizes run from 124M to 36.2B parameters. The longest trained context is 512K tokens.
About the Seed GGUF models
Seed is represented on ggufmodels.com by 111 GGUF models, quantized by 49 uploaders on Hugging Face. The most downloaded are Hermes 4_3_36b, Seed-Oss-36B-Instruct and Seed-Coder-8B-Reasoning. Parameter counts run from 124M to 36.2B, and the longest trained context window is 512K tokens.
A Q4_K_M file of a Seed model is between 0.1 to 21.8 GB, which is the quant most people start with. Most files come from mradermacher (32), DevQuasar (8) and tensorblock (7). The quants you will meet most often are Q4_K_M (85), Q2_K (70), Q6_K (68) and Q5_K_M (66), where the number is how many models offer that quant.
Frequently asked questions
Which Seed GGUF should I download?
The most downloaded Seed GGUF here is Hermes 4_3_36b. 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 Seed model need?
Q4_K_M files of Seed models on this site range from 0.1 to 21.8 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 Seed GGUF files come from?
The most common quantizers here are mradermacher, DevQuasar and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.