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
11 units shown · sorted by score
| # | Hardware | Tier | Score | Data |
|---|---|---|---|---|
| 1 | AMD Radeon RX 7900 XTX amd · enthusiast · 24GB | C | 420 | Estimated |
| 2 | AMD Radeon RX 7900 XT amd · enthusiast · 20GB | C | 365 | Estimated |
| 3 | AMD Radeon RX 9060 XT amd · mid · 16GB | C | 339 | Estimated |
| 4 | AMD Radeon RX 9070 XT amd · high · 16GB | C | 332 | Estimated |
| 5 | AMD Radeon RX 9070 amd · high · 16GB | C | 332 | Estimated |
| 6 | AMD Radeon RX 7800 XT amd · high · 16GB | C | 329 | Estimated |
| 7 | AMD Radeon RX 7900 GRE amd · high · 16GB | C | 319 | Estimated |
| 8 | AMD Radeon RX 6950 XT amd · enthusiast · 16GB | C | 316 | Estimated |
| 9 | AMD Radeon RX 6800 amd · high · 16GB | C | 304 | Estimated |
| 10 | AMD Radeon RX 6800 XT amd · enthusiast · 16GB | C | 302 | Estimated |
| 11 | AMD Radeon RX 6900 XT amd · enthusiast · 16GB | C | 302 | 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.