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

Quantization

2 · Use case

Agentic coding

Chat & writing

Coding

Documents & research

Multimodal

Automation & serving

3 · Tool & runtime

Tool: OpenCode

Runtime

4 · Workload

Context

Project size, agent behaviour, other apps

Coding style

Repository size

Repository size is a signal for retrieval and prompt-processing load — the whole repo never goes into the context.

How does the agent behave?

What else do you normally run while coding?

This memory is subtracted before the model is considered. Very important on 16–32 GB machines.

5 · Desired experience

6 · Budget & vendors (optional)

Prices are approximate launch prices for the whole system.

USD max

AppleNVIDIAAMDIntel

Qwen3 32B · Agentic coding / medium repository

Target: comfortable · 1 machines meet it

Meets your comfortable target (1)

Cheapest first.

Comfortable

Desktop PC · RTX PRO 6000 Blackwell · 128 GB RAM

96 GB VRAM (1792 GB/s) + 128 GB RAM

Quant / runtime: Q6 · Ollama
Generation: 25–35 tok/s
Per step: ≈20 s
Headroom: 60 GB

$17,284Calibrated

Meets the acceptable target (25)

Usable, with noticeable compromises for this workload.

Acceptable

Desktop PC · GeForce RTX 5090 · 32 GB RAM

32 GB VRAM (1792 GB/s) + 32 GB RAM

Quant / runtime: Q4 · Ollama
Generation: 40–50 tok/s
Per step: ≈15 s
Headroom: 3.2 GB

$2,900Calibrated

Acceptable

Desktop PC · GeForce RTX 5090 · 64 GB RAM

32 GB VRAM (1792 GB/s) + 64 GB RAM

Quant / runtime: Q4 · Ollama
Generation: 40–50 tok/s
Per step: ≈15 s
Headroom: 3.2 GB

$3,028Calibrated

Acceptable

Desktop PC · 2× GeForce RTX 3090 (48 GB) · 128 GB RAM

48 GB VRAM (936 GB/s) + 128 GB RAM

Quant / runtime: Q5 · Ollama
Generation: 16–25 tok/s
Per step: ≈30 s
Headroom: 16 GB

$2,884Estimated

Acceptable

Desktop PC · Radeon AI PRO R9700 · 32 GB RAM

32 GB VRAM (640 GB/s) + 32 GB RAM

Quant / runtime: Q4 · Lemonade
Generation: 19–25 tok/s
Per step: ≈30 s
Headroom: 3.2 GB

$2,200Calibrated

Acceptable

Desktop PC · Radeon AI PRO R9700 · 64 GB RAM

32 GB VRAM (640 GB/s) + 64 GB RAM

Quant / runtime: Q4 · Lemonade
Generation: 19–25 tok/s
Per step: ≈30 s
Headroom: 3.2 GB

$2,328Calibrated

Acceptable

Mac Studio M5 Ultra 128 GB

128 GB unified memory · 1228 GB/s

Quant / runtime: Q6 · LM Studio
Generation: 15–25 tok/s
Per step: ≈30 s
Headroom: 81 GB

$5,499Estimated

Acceptable

Mac Studio M5 Ultra 256 GB

256 GB unified memory · 1228 GB/s

Quant / runtime: Q6 · LM Studio
Generation: 15–25 tok/s
Per step: ≈30 s
Headroom: 209 GB

$6,299Estimated

Acceptable

Mac Studio M5 Ultra 512 GB

512 GB unified memory · 1228 GB/s

Quant / runtime: Q6 · LM Studio
Generation: 15–25 tok/s
Per step: ≈30 s
Headroom: 465 GB

$7,099Estimated

Acceptable

MacBook Pro M5 Max 48 GB

48 GB unified memory · 614 GB/s

Quant / runtime: Q4 · LM Studio
Generation: 13–20 tok/s
Per step: ≈40 s
Headroom: 9.7 GB

$3,999Estimated

Can run, but below your target (55)

The model loads, but the experience falls short for this workload.

Cannot run (47)

Not enough usable memory, or no compatible runtime.