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

GLM-4.6V-Flash (10B) · 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 (96)

Usable, with noticeable compromises for this workload.

Acceptable

Desktop PC · GeForce RTX 3090 · 32 GB RAM

24 GB VRAM (936 GB/s) + 32 GB RAM

Quant / runtime: Q8 · Ollama
Generation: 50–65 tok/s
Per step: ≈8 s
Headroom: 11 GB

$1,700Calibrated

Acceptable

Desktop PC · GeForce RTX 3090 · 64 GB RAM

24 GB VRAM (936 GB/s) + 64 GB RAM

Quant / runtime: Q8 · Ollama
Generation: 50–65 tok/s
Per step: ≈8 s
Headroom: 11 GB

$1,828Calibrated

Acceptable

Desktop PC · GeForce RTX 4060 Ti 16GB · 32 GB RAM

16 GB VRAM (288 GB/s) + 32 GB RAM

Quant / runtime: Q8 · Ollama
Generation: 13–20 tok/s
Per step: ≈25 s
Headroom: 3.4 GB

$1,350Estimated

Acceptable

Desktop PC · GeForce RTX 4070 Ti SUPER · 32 GB RAM

16 GB VRAM (672 GB/s) + 32 GB RAM

Quant / runtime: Q8 · Ollama
Generation: 30–50 tok/s
Per step: ≈10 s
Headroom: 3.4 GB

$1,700Estimated

Acceptable

Desktop PC · GeForce RTX 4080 SUPER · 32 GB RAM

16 GB VRAM (736 GB/s) + 32 GB RAM

Quant / runtime: Q8 · Ollama
Generation: 40–55 tok/s
Per step: ≈9 s
Headroom: 3.4 GB

$1,900Calibrated

Acceptable

Desktop PC · GeForce RTX 4090 · 32 GB RAM

24 GB VRAM (1008 GB/s) + 32 GB RAM

Quant / runtime: Q8 · Ollama
Generation: 55–75 tok/s
Per step: ≈6 s
Headroom: 11 GB

$2,700Calibrated

Acceptable

Desktop PC · GeForce RTX 4090 · 64 GB RAM

24 GB VRAM (1008 GB/s) + 64 GB RAM

Quant / runtime: Q8 · Ollama
Generation: 55–75 tok/s
Per step: ≈6 s
Headroom: 11 GB

$2,828Calibrated

Acceptable

Desktop PC · GeForce RTX 5060 Ti 16GB · 32 GB RAM

16 GB VRAM (448 GB/s) + 32 GB RAM

Quant / runtime: Q8 · Ollama
Generation: 25–35 tok/s
Per step: ≈15 s
Headroom: 3.4 GB

$1,330Calibrated

Acceptable

Desktop PC · GeForce RTX 5070 Ti · 32 GB RAM

16 GB VRAM (896 GB/s) + 32 GB RAM

Quant / runtime: Q8 · Ollama
Generation: 55–70 tok/s
Per step: ≈7 s
Headroom: 3.4 GB

$1,650Calibrated

Can run, but below your target (15)

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

Cannot run (17)

Not enough usable memory, or no compatible runtime.