Try a Mac Studio M5 Ultra before you buy one
A Mac Studio for local AI is a big purchase. Before you spend the money, run your own prompts and your own code on one, and compare it side by side with a Mac mini M6.
Free: 2 chat questions and 2 minutes with your coding agent. No card needed.
- Your real workload. Your prompts, your repository, your coding agent, not a canned demo.
- Two machines to compare. The same small model runs on both; the large models only fit on the Ultra. All numbers are our own measurements, missing ones are marked.
- Find out what fits. The calculator tells you which model sizes fit into which memory.
The models
| Model | Chip | Generation | Reading | First token | Power while answering |
|---|---|---|---|---|---|
| Qwen3.8-Flash-Next 180B · 4-bit + MTP · 74.7 GB | Mac Studio M5 Ultra 96 GB | 80 tok/s | 3,270 tok/s | 0.12 s | 38 W |
| Mac mini M6 16 GB | does not fit | ||||
| Ornith-1.5 122B 122B · 4-bit · 65.5 GB | Mac Studio M5 Ultra 96 GB | 125 tok/s | 3,246 tok/s | 0.05 s | measurement coming |
| Mac mini M6 16 GB | does not fit | ||||
| Ornith-1.5 9B 9B · 4-bit · 4.8 GB | Mac Studio M5 Ultra 96 GB | 161 tok/s | 5,193 tok/s | 0.03 s | measurement coming |
| Mac mini M6 16 GB | 26 tok/s | 998 tok/s | 0.17 s | 7.6 W | |
How it works
- Enter your email, confirm the code. No password, no card.
- 2 free questions in the chat, with live numbers.
- 2 free minutes with your own coding agent – it wraps up with a summary when time is up.
FAQ
What is Try Silicon?
Two real Macs in our lab running open language models locally: a Mac Studio with M5 Ultra and 96 GB unified memory for large models, and a Mac mini with M6 and 16 GB for comparison. Test both live before you buy hardware or build your own setup.
Why is there also a Mac mini M6?
To show honestly what a big machine adds – and what a small one can already do. The large models don't fit into 16 GB at all, but a small 9B model runs smoothly and efficiently on the M6. You can test both yourself; all numbers are our own measurements, missing ones are marked.
What is included for free?
2 questions in the chat and 2 minutes with your coding agent, starting with its first request – shared across both machines. When the time is up, your agent gets one last answer: what's done and what would still be open.
Which models are available?
The M5 Ultra runs Qwen3.8-Flash-Next, a 180B mixture-of-experts model with 512 experts. The Mac mini M6 runs the small Ornith-1.5 9B live. We show Ornith's 122B model with measurements for comparison. Only one large model fits into the Ultra's memory at a time.
M5 Ultra vs. Mac mini M6Does the model fit on my Mac?Rent a Mac Studio M5 Ultra by the hourOpenAI- and Anthropic-compatible API on a Mac Studio M5 UltraQwen3.8-Flash-NextOrnith-1.5 122BOrnith-1.5 9B
Ready to feel it?
No credit card required for the free test.