General GGUF models
134659 GGUF models: general chat and instruction-following models. Sizes run from 0M to 20260731B parameters. The longest trained context is 4194304K tokens.
About General GGUF models
134,659 GGUF models are filed under General: general chat and instruction-following models. The most downloaded are Ornith 1.0 9B, MiniMax H3 and Qwen Image 2.1. Parameter counts run from 0M to 20260731B, and the longest trained context window is 4194304K tokens.
General models are the broadest choice for chat and instruction following. Start with the size that fits your GPU, then pick a quant. The families you will see most are Llama (26695), Qwen (12868) and Gemma (7914).
Frequently asked questions
What are General GGUF models?
General chat and instruction-following models. There are 134,659 of them on this site.
Which General GGUF model should I start with?
The most downloaded is Ornith 1.0 9B. Choose the size that fits your GPU, then a Q4_K_M quant unless you have memory to spare.