Medium GGUF models
42835 GGUF models with roughly 10B to 34B parameters. Sizes run from 9.51B to 34B parameters. The longest trained context is 10240K tokens.
What counts as a medium model?
On this site medium means roughly 10B to 34B parameters. A Q4_K_M file is usually 6 to 22 GB, so you need a 12 GB to 24 GB GPU. 42,835 models fit this class. The most downloaded are Qwen3.8-27B, Qwen3.8-27B and Qwen3.8 27B Uncensored.
Their Q4_K_M files run 0.0 to 150.2 GB. The families you will see most are Qwen (8111), Gemma (3493) and Mistral (2318). The size class sorts models by parameter count, so a model with more experts or a longer context can need more memory than its class suggests. The model pages show the real file sizes.
Frequently asked questions
How much VRAM does a medium GGUF model need?
A Q4_K_M file is usually 6 to 22 GB, so you need a 12 GB to 24 GB GPU.
Which medium GGUF model is the most popular?
By Hugging Face downloads, Qwen3.8-27B.