Explore AI
Mac with 8 GB
Workable, but only just — and not as a daily driver for anything serious.
Workable, but only just — and not as a daily driver for anything serious.
- Platform
- Apple Silicon
- Memory
- 8 GB unified
The operating system and browser already want most of this. A 3–4B model at Q4 will leave little room for a long context, and the machine will run warm.
Runs comfortably
- Qwen3 1.7B 3 GB at Q4 Apache-2.0
- Llama 3.2 1B Instruct 2 GB at Q4 Llama 3.2 Community
- Qwen3 4B 5 GB at Q4 Apache-2.0
Will not fit
- Qwen3 8Bneeds about 8 GB
- Qwen3 32Bneeds about 24 GB
Worth knowing
If this is your machine, the honest advice is to use a hosted model for real work and keep a tiny local model for offline or private scraps.