What hardware do I need?
Hardware that delivers the experience you want — not just loads the model
Pick the model and describe the workload. We rate every machine in the database for that exact workload and group them by whether they meet your target.
1 · Model
2 · Use case
Agentic coding
Chat & writing
Coding
Documents & research
Multimodal
Automation & serving
3 · Tool & runtime
Tool: OpenCode
4 · Workload
Project size, agent behaviour, other apps
5 · Desired experience
6 · Budget & vendors (optional)
Prices are approximate launch prices for the whole system.
Llama 3.3 70B Instruct · Agentic coding / medium repository
Target: comfortable · 0 machines meet it
Meets your comfortable target (0)
Cheapest first.
No machine in the database meets this target. Try a smaller model, shorter context or a lighter workload.
Meets the acceptable target (4)
Usable, with noticeable compromises for this workload.
Desktop PC · RTX PRO 6000 Blackwell · 128 GB RAM
96 GB VRAM (1792 GB/s) + 128 GB RAM
- Quant / runtime
- Q5 · Ollama
- Generation
- 16–20 tok/s
- Per step
- ≈25 s
- Headroom
- 36 GB
Mac Studio M5 Ultra 128 GB
128 GB unified memory · 1228 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 10–17 tok/s
- Per step
- ≈35 s
- Headroom
- 66 GB
Mac Studio M5 Ultra 256 GB
256 GB unified memory · 1228 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 10–17 tok/s
- Per step
- ≈35 s
- Headroom
- 194 GB
Mac Studio M5 Ultra 512 GB
512 GB unified memory · 1228 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 10–17 tok/s
- Per step
- ≈35 s
- Headroom
- 450 GB
Can run, but below your target (44)
The model loads, but the experience falls short for this workload.
Cannot run (80)
Not enough usable memory, or no compatible runtime.