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.
Qwen3-Next 80B-A3B Instruct · Agentic coding / medium repository
Target: comfortable · 23 machines meet it
Meets your comfortable target (23)
Cheapest first.
Ryzen AI Max+ 395 mini PC / Framework Desktop · 128 GB
128 GB unified memory · 256 GB/s
- Quant / runtime
- Q6 · Lemonade
- Generation
- 50–65 tok/s
- Per step
- ≈10 s
- Headroom
- 49 GB
Mac Studio M2 Max 96 GB
96 GB unified memory · 400 GB/s
- Quant / runtime
- Q6 · LM Studio
- Generation
- 60–80 tok/s
- Per step
- ≈8 s
- Headroom
- 20 GB
MacBook Pro M3 Max 96 GB
96 GB unified memory · 300 GB/s
- Quant / runtime
- Q6 · LM Studio
- Generation
- 45–65 tok/s
- Per step
- ≈10 s
- Headroom
- 20 GB
Mac Studio M4 Max 128 GB
128 GB unified memory · 546 GB/s
- Quant / runtime
- Q6 · LM Studio
- Generation
- 80–110 tok/s
- Per step
- ≈6 s
- Headroom
- 52 GB
Mac Studio M5 Max 128 GB
128 GB unified memory · 614 GB/s
- Quant / runtime
- Q6 · LM Studio
- Generation
- 75–130 tok/s
- Per step
- ≈4 s
- Headroom
- 52 GB
MacBook Pro M2 Max 96 GB
96 GB unified memory · 400 GB/s
- Quant / runtime
- Q6 · LM Studio
- Generation
- 60–80 tok/s
- Per step
- ≈8 s
- Headroom
- 20 GB
MacBook Pro M3 Max 128 GB
128 GB unified memory · 400 GB/s
- Quant / runtime
- Q6 · LM Studio
- Generation
- 60–85 tok/s
- Per step
- ≈8 s
- Headroom
- 52 GB
MacBook Pro M4 Max 128 GB
128 GB unified memory · 546 GB/s
- Quant / runtime
- Q6 · LM Studio
- Generation
- 80–110 tok/s
- Per step
- ≈6 s
- Headroom
- 52 GB
Mac Studio M3 Ultra 96 GB
96 GB unified memory · 819 GB/s
- Quant / runtime
- Q6 · LM Studio
- Generation
- 85–110 tok/s
- Per step
- ≈5 s
- Headroom
- 20 GB
Meets the acceptable target (16)
Usable, with noticeable compromises for this workload.
NVIDIA DGX Spark (GB10) · 64 GB
64 GB unified memory · 273 GB/s
- Quant / runtime
- Q4 · Ollama
- Generation
- 65–85 tok/s
- Per step
- ≈6 s
- Headroom
- 7.4 GB
MacBook Pro M1 Max 64 GB
64 GB unified memory · 400 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 80–110 tok/s
- Per step
- ≈7 s
- Headroom
- 6.7 GB
MacBook Pro M2 Max 64 GB
64 GB unified memory · 400 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 80–110 tok/s
- Per step
- ≈7 s
- Headroom
- 6.7 GB
MacBook Pro M3 Max 64 GB
64 GB unified memory · 400 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 80–110 tok/s
- Per step
- ≈6 s
- Headroom
- 6.7 GB
MacBook Pro M4 Max 64 GB
64 GB unified memory · 546 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 110–150 tok/s
- Per step
- ≈5 s
- Headroom
- 6.7 GB
MacBook Pro M5 Pro 64 GB
64 GB unified memory · 307 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 50–85 tok/s
- Per step
- ≈7 s
- Headroom
- 6.7 GB
MacBook Pro M5 Max 64 GB
64 GB unified memory · 614 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 100–170 tok/s
- Per step
- ≈3 s
- Headroom
- 6.7 GB
Mac mini M4 Pro 64 GB
64 GB unified memory · 273 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 55–80 tok/s
- Per step
- ≈9 s
- Headroom
- 6.7 GB
Mac mini M5 Pro 64 GB
64 GB unified memory · 307 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 50–85 tok/s
- Per step
- ≈7 s
- Headroom
- 6.7 GB
Can run, but below your target (11)
The model loads, but the experience falls short for this workload.
Cannot run (78)
Not enough usable memory, or no compatible runtime.