Rent a Mac Studio M5 Ultra by the hour: test local LLMs in the cloud
You don't have to buy a Mac Studio to find out what it can do. Ours is online: 96 GB of unified memory, a 180B model loaded, reachable from your browser or from your own tools. The first test is free, after that 1 h costs €5.
Free: 2 chat questions and 2 minutes with your coding agent. No card needed.
- Real hardware, no simulation. Every request runs on one physical Mac Studio M5 Ultra, one request at a time. The speed you see is the speed the machine delivers.
- No setup. Sign in with an email code, chat in the browser or connect your coding agent with an API key.
- Pay by the hour, no subscription. A time pass starts right away and simply runs out.
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 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.
How much is a time pass?
1 h: €5. With a pass: unlimited chat and agent access plus priority in the queue of the chosen machine. Another pass for the same machine extends the current one. No subscription.
Why is there a queue?
To keep the numbers honest, each machine runs only one request at a time – every answer gets full speed. Each machine has its own queue, so you can e.g. let your agent work on the M5 Ultra and chat on the M6 at the same time. Paid requests go first; free requests move up after 90 seconds at the latest.
Is my code stored?
We do not store chats or prompts – only counts like tokens and speed. To make follow-up requests fast, the machine keeps a cache of recently processed text on its SSD, which is overwritten automatically. Please do not send secrets.
M5 Ultra vs. Mac mini M6Does the model fit on my Mac?OpenAI- and Anthropic-compatible API on a Mac Studio M5 UltraTry a Mac Studio M5 Ultra before you buy oneQwen3.8-Flash-NextOrnith-1.5 122BOrnith-1.5 9B
Ready to feel it?
No credit card required for the free test.