Every catalog hardware unit ranked by composite score (0–1000): measured tok/s, VRAM fit, ecosystem support, perf-per-watt. 2 of 128 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
53 units shown · sorted by score
| # | Hardware | Tier | Score | Data |
|---|---|---|---|---|
| 1 | NVIDIA GeForce GTX 1080 nvidia · mid · 8GB | D | 286 | Estimated |
| 2 | NVIDIA RTX PRO 6000 Blackwell nvidia · workstation · 96GB | D | 280 | Estimated |
| 3 | NVIDIA GB200 NVL72 nvidia · workstation · 13824GB | D | 280 | Estimated |
| 4 | NVIDIA B200 nvidia · workstation · 192GB | D | 280 | Estimated |
| 5 | NVIDIA H200 nvidia · workstation · 141GB | D | 280 | Estimated |
| 6 | NVIDIA H100 NVL nvidia · workstation · 188GB | D | 280 | Estimated |
| 7 | NVIDIA RTX 6000 Ada Generation nvidia · workstation · 48GB | D | 273 | Estimated |
| 8 | NVIDIA L40S nvidia · workstation · 48GB | D | 273 | Estimated |
| 9 | NVIDIA L40 nvidia · workstation · 48GB | D | 273 | Estimated |
| 10 | NVIDIA H100 PCIe nvidia · workstation · 80GB | D | 273 | Estimated |
| 11 | NVIDIA A40 nvidia · workstation · 48GB | D | 273 | Estimated |
| 12 | NVIDIA RTX A6000 (Ampere) nvidia · workstation · 48GB | D | 273 | Estimated |
| 13 | NVIDIA A100 80GB SXM nvidia · workstation · 80GB | D | 273 | Estimated |
| 14 | NVIDIA H100 SXM nvidia · workstation · 80GB | D | 273 | Estimated |
| 15 | NVIDIA GeForce GTX 1070 nvidia · mid · 8GB | D | 270 | Estimated |
| 16 | NVIDIA GeForce GTX 1070 Ti nvidia · mid · 8GB | D | 268 | Estimated |
| 17 | NVIDIA GeForce RTX 3050 nvidia · entry · 8GB | D | 263 | Estimated |
| 18 | NVIDIA GeForce GTX 1660 Super nvidia · mid · 6GB | D | 261 | Estimated |
| 19 | NVIDIA GeForce RTX 3090 Ti nvidia · enthusiast · 24GB | D | 259 | Estimated |
| 20 | NVIDIA GeForce RTX 5090 Mobile nvidia · enthusiast · 24GB | D | 259 | Estimated |
| 21 | NVIDIA A100 40GB nvidia · workstation · 40GB | D | 259 | Estimated |
| 22 | NVIDIA L4 nvidia · workstation · 24GB | D | 259 | Estimated |
| 23 | NVIDIA RTX 5000 Ada Generation nvidia · workstation · 32GB | D | 259 | Estimated |
| 24 | Razer Blade 16 (2025, RTX 5090 Mobile) nvidia · enthusiast · 24GB | D | 259 | Estimated |
| 25 | ASUS ROG Strix Scar 18 (RTX 5090 Mobile) nvidia · enthusiast · 24GB | D | 259 | Estimated |
| 26 | NVIDIA RTX A5000 nvidia · workstation · 24GB | D | 259 | Estimated |
| 27 | NVIDIA GeForce RTX 2060 nvidia · mid · 6GB | D | 257 | Estimated |
| 28 | NVIDIA GeForce GTX 1660 Ti nvidia · mid · 6GB | D | 247 | Estimated |
| 29 | NVIDIA GeForce RTX 5070 Ti nvidia · high · 16GB | D | 238 | Estimated |
| 30 | NVIDIA GeForce RTX 4080 nvidia · high · 16GB | D | 238 | Estimated |
| 31 | NVIDIA GeForce RTX 4070 Ti Super nvidia · high · 16GB | D | 238 | Estimated |
| 32 | NVIDIA GeForce RTX 5060 Ti 16GB nvidia · mid · 16GB | D | 238 | Estimated |
| 33 | Lenovo Legion 5 Pro Gen 7 (RTX 3080 16GB) nvidia · high · 16GB | D | 238 | Estimated |
| 34 | NVIDIA GeForce RTX 4090 Mobile nvidia · enthusiast · 16GB | D | 238 | Estimated |
| 35 | NVIDIA GeForce RTX 3050 Ti (Mobile) nvidia · mobile · 4GB | D | 224 | Estimated |
| 36 | NVIDIA GeForce GTX 1650 Super nvidia · entry · 4GB | D | 221 | Estimated |
| 37 | NVIDIA GeForce GTX 1060 6GB nvidia · entry · 6GB | D | 218 | Estimated |
| 38 | NVIDIA GeForce GTX 1660 nvidia · mid · 6GB | D | 218 | Estimated |
| 39 | NVIDIA GeForce GTX 1060 3GB nvidia · entry · 3GB | D | 218 | Estimated |
| 40 | NVIDIA GeForce RTX 4070 Ti nvidia · high · 12GB | D | 217 | Estimated |
| 41 | NVIDIA GeForce RTX 4070 nvidia · mid · 12GB | D | 217 | Estimated |
| 42 | NVIDIA GeForce RTX 3080 12GB nvidia · high · 12GB | D | 217 | Estimated |
| 43 | NVIDIA GeForce RTX 5070 nvidia · mid · 12GB | D | 217 | Estimated |
| 44 | NVIDIA GeForce RTX 4070 Super nvidia · mid · 12GB | D | 217 | Estimated |
| 45 | NVIDIA GeForce GTX 1650 nvidia · entry · 4GB | D | 204 | Estimated |
| 46 | NVIDIA GeForce GTX 1050 Ti nvidia · entry · 4GB | D | 198 | Estimated |
| 47 | NVIDIA GeForce RTX 4060 Ti 8GB nvidia · mid · 8GB | D | 196 | Estimated |
| 48 | NVIDIA GeForce RTX 4060 nvidia · entry · 8GB | D | 196 | Estimated |
| 49 | NVIDIA GeForce RTX 3080 10GB nvidia · high · 10GB | D | 196 | Estimated |
| 50 | NVIDIA GeForce RTX 5060 nvidia · entry · 8GB | D | 196 | Estimated |
| 51 | NVIDIA GeForce RTX 3070 nvidia · mid · 8GB | D | 196 | Estimated |
| 52 | NVIDIA GeForce RTX 5060 Ti 8GB nvidia · mid · 8GB | D | 196 | Estimated |
| 53 | NVIDIA DGX Spark (Project Digits) nvidia · workstation | D | 140 | Estimated |
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.