Every catalog hardware unit ranked by composite score (0–1000): measured tok/s, VRAM fit, ecosystem support, perf-per-watt. 2 of 154 ranks anchored to a measured benchmark — the rest are honestly flagged as extrapolated or estimated.
Methodology: /methodology · Run your own: curl -fsSL runlocalai.co/bench.mjs -o bench.mjs && node bench.mjs
8 units shown · sorted by score
| # | Hardware | Tier | Score | Data |
|---|---|---|---|---|
| 1 | Apple M4 Max apple · enthusiast | C | 457 | Estimated |
| 2 | MacBook Pro 16" M4 Max apple · enthusiast | C | 445 | Estimated |
| 3 | Apple Mac Studio (M4 Max) apple · enthusiast | C | 438 | Estimated |
| 4 | Apple M1 Max apple · high | C | 404 | Estimated |
| 5 | Apple M2 Max apple · high | C | 400 | Estimated |
| 6 | Apple M3 Max apple · enthusiast | C | 398 | Estimated |
| 7 | Apple M4 Pro apple · high | C | 351 | Estimated |
| 8 | Apple Mac Mini (M4 Pro) apple · high | C | 340 | Estimated |
Amazon search links — we may earn a small commission at no extra cost to you. How we make money.
Steady-state tok/s on a representative 7B/8B Q4 model. Measured from real benchmark rows, or extrapolated from VRAM bandwidth × runtime-stack efficiency.
How comfortably the rig holds 7B / 32B / 70B class models. Apple unified memory counts; NPU/SoC system RAM counts.
CUDA / MLX / ROCm / Vulkan reach. Real-world friction the operator hits when installing tools.
Tok/s per watt. Mobile / NPU class scores well; dense desktop GPUs trade efficiency for absolute throughput.
A confidence multiplier (1.0 measured · 0.85 extrapolated · 0.7 estimated) discounts the headline so we don't pretend to know more than we do. Score is recomputed on every page load against the latest catalog + benchmark data — submit your own run with runlocalai-bench --submit --hardware your-rig to firm up the numbers.