Explore AI
Mac with 16 GB
The real starting point for local AI.
The real starting point for local AI.
- Platform
- Apple Silicon
- Memory
- 16 GB unified
An 8B model at Q4 fits with room for a decent context. Expect useful speed. This is where local AI stops being a toy.
Runs comfortably
- Qwen3 8B 8 GB at Q4 Apache-2.0
- Llama 3.1 8B Instruct 8 GB at Q4 Llama 3.1 Community
- Qwen3 4B 5 GB at Q4 Apache-2.0
Will not fit
- Qwen3 32Bneeds about 24 GB
- Gemma 4 31Bneeds about 24 GB
Worth knowing
16 GB is the sweet spot most people should aim for. Below it you are compromising on model size, which matters more than anything else.