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.
GLM-4.7-Flash (30B-A3B) · Agentic coding / medium repository
Target: comfortable · 66 machines meet it
Meets your comfortable target (66)
Cheapest first.
Desktop PC · Intel Arc Pro B60 24GB · 32 GB RAM
24 GB VRAM (456 GB/s) + 32 GB RAM
- Quant / runtime
- Q4 · LM Studio
- Generation
- 45–75 tok/s
- Per step
- ≈20 s
- Headroom
- 3.3 GB
Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB
64 GB unified memory · 256 GB/s
- Quant / runtime
- Q6 · Lemonade
- Generation
- 40–55 tok/s
- Per step
- ≈15 s
- Headroom
- 23 GB
Desktop PC · Intel Arc Pro B60 24GB · 64 GB RAM
24 GB VRAM (456 GB/s) + 64 GB RAM
- Quant / runtime
- Q4 · LM Studio
- Generation
- 45–75 tok/s
- Per step
- ≈20 s
- Headroom
- 3.3 GB
Desktop PC · GeForce RTX 3090 · 32 GB RAM
24 GB VRAM (936 GB/s) + 32 GB RAM
- Quant / runtime
- Q4 · Ollama
- Generation
- 130–180 tok/s
- Per step
- ≈4 s
- Headroom
- 3.4 GB
Mac mini M4 Pro 48 GB
48 GB unified memory · 273 GB/s
- Quant / runtime
- Q6 · LM Studio
- Generation
- 35–50 tok/s
- Per step
- ≈20 s
- Headroom
- 10 GB
Desktop PC · Radeon RX 7900 XTX · 32 GB RAM
24 GB VRAM (960 GB/s) + 32 GB RAM
- Quant / runtime
- Q4 · Lemonade
- Generation
- 150–210 tok/s
- Per step
- ≈4 s
- Headroom
- 3.4 GB
Desktop PC · GeForce RTX 3090 · 64 GB RAM
24 GB VRAM (936 GB/s) + 64 GB RAM
- Quant / runtime
- Q4 · Ollama
- Generation
- 130–180 tok/s
- Per step
- ≈4 s
- Headroom
- 3.4 GB
Desktop PC · Radeon RX 7900 XTX · 64 GB RAM
24 GB VRAM (960 GB/s) + 64 GB RAM
- Quant / runtime
- Q4 · Lemonade
- Generation
- 150–210 tok/s
- Per step
- ≈4 s
- Headroom
- 3.4 GB
Ryzen AI Max+ 395 mini PC / Framework Desktop · 128 GB
128 GB unified memory · 256 GB/s
- Quant / runtime
- Q6 · Lemonade
- Generation
- 40–55 tok/s
- Per step
- ≈15 s
- Headroom
- 87 GB
Meets the acceptable target (15)
Usable, with noticeable compromises for this workload.
MacBook Pro M3 Pro 36 GB
36 GB unified memory · 150 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 25–35 tok/s
- Per step
- ≈25 s
- Headroom
- 6.7 GB
MacBook Air M4 32 GB
32 GB unified memory · 120 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 20–25 tok/s
- Per step
- ≈35 s
- Headroom
- 2.8 GB
MacBook Air M5 32 GB
32 GB unified memory · 153 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 20–35 tok/s
- Per step
- ≈20 s
- Headroom
- 2.8 GB
MacBook Pro M1 Pro 32 GB
32 GB unified memory · 200 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 35–45 tok/s
- Per step
- ≈25 s
- Headroom
- 2.8 GB
MacBook Pro M1 Max 32 GB
32 GB unified memory · 400 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 60–85 tok/s
- Per step
- ≈10 s
- Headroom
- 2.8 GB
MacBook Pro M2 Pro 32 GB
32 GB unified memory · 200 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 35–45 tok/s
- Per step
- ≈20 s
- Headroom
- 2.8 GB
MacBook Pro M2 Max 32 GB
32 GB unified memory · 400 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 65–85 tok/s
- Per step
- ≈10 s
- Headroom
- 2.8 GB
MacBook Pro M4 32 GB
32 GB unified memory · 120 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 20–25 tok/s
- Per step
- ≈35 s
- Headroom
- 2.8 GB
MacBook Pro M5 32 GB
32 GB unified memory · 153 GB/s
- Quant / runtime
- Q4 · LM Studio
- Generation
- 20–35 tok/s
- Per step
- ≈20 s
- Headroom
- 2.8 GB
Can run, but below your target (15)
The model loads, but the experience falls short for this workload.
Cannot run (32)
Not enough usable memory, or no compatible runtime.