Hardware matrix
Compare models across hardware
Which local models run on which machines. Y runs comfortably, ≈ is a tight fit, N needs more memory. Computed from the same validated memory math as every can-i-run page.
Choosing between your hardware and a hosted API? Compare local models with Astra, Claude and Gemini using Arena preference ratings, memory fit and monthly token costs.
Already know you need an API? Browse hosted models and estimate monthly API cost from dated vendor rates.
| Model | Nvidia GeForce RTX 2060 6 GB | iPhone 17 8 GB | iPhone 17 Pro 12 GB | 16GB RAM Laptop 16 GB | Samsung Galaxy S26 Ultra 16 GB | Apple M4 Pro 24 GB | Apple M4 Pro 48 GB | Apple M3 Ultra 256 GB |
|---|---|---|---|---|---|---|---|---|
| SmolLM2 135M | Y | Y | Y | Y | Y | Y | Y | Y |
| SmolLM2 1.7B | Y | Y | Y | Y | Y | Y | Y | Y |
| Phi-4-mini-reasoning | Y | ≈ | Y | Y | Y | Y | Y | Y |
| Ministral 3 8B | N | N | Y | Y | Y | Y | Y | Y |
| Gemma 4 12B | N | N | N | Y | Y | Y | Y | Y |
| Devstral Small 2 24B | N | N | N | N | N | ≈ | Y | Y |
| Qwen2.5 32B | N | N | N | N | N | N | Y | Y |
| SE Seed-OSS 36B Instruct | N | N | N | N | N | N | Y | Y |
| DO dots.llm1 | N | N | N | N | N | N | N | Y |
| KI Kimi K3 | N | N | N | N | N | N | N | N |
This is a representative slice. For any exact pairing across all 161 models and 49 devices, open its can-i-run page or use the detector.
FAQ
How do I compare local AI models across different hardware?
Match each model's memory need at Q4_K_M to the device's usable memory. This matrix does it for 10 representative models across 8 devices; Y means it runs comfortably, ≈ means a tight fit, N means not enough memory. For any exact pairing across all 161 models and 49 devices, open its can-i-run page.