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
79 units shown · sorted by score
| # | Hardware | Tier | Score | Data |
|---|---|---|---|---|
| 1 | NVIDIA H20 (96GB) nvidia · workstation · 96GB | B | 697 | Estimated |
| 2 | NVIDIA H200 NVL (PCIe) nvidia · workstation · 141GB | B | 684 | Estimated |
| 3 | NVIDIA B200 nvidia · workstation · 192GB | B | 684 | Estimated |
| 4 | NVIDIA H200 nvidia · workstation · 141GB | B | 676 | Estimated |
| 5 | NVIDIA B300 (Blackwell Ultra) nvidia · workstation · 288GB | B | 669 | Estimated |
| 6 | NVIDIA H100 NVL nvidia · workstation · 188GB | B | 663 | Estimated |
| 7 | NVIDIA H100 PCIe nvidia · workstation · 80GB | B | 662 | Estimated |
| 8 | NVIDIA A100 80GB SXM nvidia · workstation · 80GB | B | 657 | Estimated |
| 9 | NVIDIA H100 SXM nvidia · workstation · 80GB | B | 655 | Estimated |
| 10 | NVIDIA RTX PRO 6000 Blackwell nvidia · workstation · 96GB | B | 650 | Estimated |
| 11 | NVIDIA A100 40GB nvidia · workstation · 40GB | B | 635 | Estimated |
| 12 | NVIDIA GB200 NVL72 nvidia · workstation · 13824GB | B | 631 | Estimated |
| 13 | NVIDIA GeForce RTX 5090 nvidia · enthusiast · 32GB | B | 630 | Estimated |
| 14 | NVIDIA RTX 4090 48GB (China-mod) nvidia · workstation · 48GB | B | 534 | Estimated |
| 15 | NVIDIA RTX 5000 PRO Blackwell 48GB nvidia · workstation · 48GB | B | 529 | Estimated |
| 16 | NVIDIA RTX 6000 Ada Generation nvidia · workstation · 48GB | B | 529 | Estimated |
| 17 | NVIDIA GeForce RTX 3090 Ti nvidia · enthusiast · 24GB | B | 520 | Estimated |
| 18 | NVIDIA GeForce RTX 4090 nvidia · enthusiast · 24GB | B | 520 | Estimated |
| 19 | NVIDIA GeForce RTX 5090 Mobile nvidia · enthusiast · 24GB | B | 512 | Estimated |
| 20 | NVIDIA RTX PRO 4500 Blackwell nvidia · workstation · 32GB | B | 507 | Estimated |
| 21 | NVIDIA GeForce RTX 3090 nvidia · enthusiast · 24GB | B | 505 | Estimated |
| 22 | NVIDIA L40 nvidia · workstation · 48GB | B | 503 | Estimated |
| 23 | NVIDIA L40S nvidia · workstation · 48GB | B | 500 | Estimated |
| 24 | NVIDIA RTX A6000 (Ampere) nvidia · workstation · 48GB | C | 477 | Estimated |
| 25 | NVIDIA GeForce RTX 5070 Ti nvidia · high · 16GB | C | 477 | Estimated |
| 26 | NVIDIA RTX A5000 nvidia · workstation · 24GB | C | 468 | Estimated |
| 27 | NVIDIA A40 nvidia · workstation · 48GB | C | 458 | Estimated |
| 28 | NVIDIA GeForce RTX 3080 Ti nvidia · enthusiast · 12GB | C | 456 | Estimated |
| 29 | NVIDIA GeForce RTX 3080 12GB nvidia · high · 12GB | C | 456 | Estimated |
| 30 | NVIDIA RTX PRO 4000 Blackwell nvidia · workstation · 24GB | C | 455 | Estimated |
| 31 | NVIDIA GeForce RTX 4080 Super nvidia · high · 16GB | C | 433 | Estimated |
| 32 | NVIDIA GeForce RTX 4080 nvidia · high · 16GB | C | 428 | Estimated |
| 33 | NVIDIA GeForce RTX 4070 Ti Super nvidia · high · 16GB | C | 418 | Estimated |
| 34 | NVIDIA RTX 5000 Ada Generation nvidia · workstation · 32GB | C | 414 | Estimated |
| 35 | NVIDIA RTX 2080 Ti 22GB (China-mod) nvidia · mid · 22GB | C | 405 | Estimated |
| 36 | NVIDIA GeForce RTX 4090 Mobile nvidia · enthusiast · 16GB | C | 400 | Estimated |
| 37 | NVIDIA GeForce RTX 5070 nvidia · mid · 12GB | C | 399 | Estimated |
| 38 | NVIDIA GeForce RTX 3080 10GB nvidia · high · 10GB | C | 397 | Estimated |
| 39 | NVIDIA GeForce RTX 5060 Ti 16GB nvidia · mid · 16GB | C | 364 | Estimated |
| 40 | NVIDIA GeForce RTX 2080 Ti nvidia · enthusiast · 11GB | C | 363 | Estimated |
| 41 | NVIDIA L4 nvidia · workstation · 24GB | C | 360 | Estimated |
| 42 | NVIDIA GeForce RTX 3070 Ti nvidia · high · 8GB | C | 358 | Estimated |
| 43 | NVIDIA GeForce RTX 4070 nvidia · mid · 12GB | C | 356 | Estimated |
| 44 | NVIDIA GeForce RTX 4070 Super nvidia · mid · 12GB | C | 355 | Estimated |
| 45 | NVIDIA GeForce RTX 4070 Ti nvidia · high · 12GB | C | 351 | Estimated |
| 46 | NVIDIA GeForce RTX 5070 Laptop GPU nvidia · high · 12GB | C | 337 | Estimated |
| 47 | NVIDIA GeForce RTX 2080 Super nvidia · high · 8GB | C | 330 | Estimated |
| 48 | NVIDIA GeForce GTX 1080 Ti nvidia · high · 11GB | C | 327 | Estimated |
| 49 | NVIDIA GeForce RTX 5060 nvidia · entry · 8GB | C | 326 | Estimated |
| 50 | NVIDIA GeForce RTX 2070 nvidia · high · 8GB | C | 323 | Estimated |
| 51 | NVIDIA GeForce RTX 2060 Super nvidia · mid · 8GB | C | 323 | Estimated |
| 52 | NVIDIA GeForce RTX 5060 Ti 8GB nvidia · mid · 8GB | C | 322 | Estimated |
| 53 | NVIDIA GeForce RTX 3060 Ti nvidia · high · 8GB | C | 321 | Estimated |
| 54 | NVIDIA GeForce RTX 4060 Ti 16GB nvidia · mid · 16GB | C | 320 | Estimated |
| 55 | NVIDIA GeForce RTX 3060 12GB nvidia · mid · 12GB | C | 319 | Estimated |
| 56 | NVIDIA GeForce RTX 3070 nvidia · mid · 8GB | C | 319 | Estimated |
| 57 | NVIDIA GeForce RTX 2070 Super nvidia · high · 8GB | C | 319 | Estimated |
| 58 | NVIDIA GeForce RTX 5050 nvidia · entry · 8GB | D | 291 | Estimated |
| 59 | NVIDIA GeForce GTX 1080 nvidia · mid · 8GB | D | 286 | Estimated |
| 60 | NVIDIA GeForce RTX 4060 nvidia · entry · 8GB | D | 279 | Estimated |
| 61 | NVIDIA GeForce RTX 4060 Ti 8GB nvidia · mid · 8GB | D | 278 | Estimated |
| 62 | NVIDIA GeForce GTX 1070 nvidia · mid · 8GB | D | 270 | Estimated |
| 63 | NVIDIA GeForce GTX 1070 Ti nvidia · mid · 8GB | D | 268 | Estimated |
| 64 | NVIDIA GeForce RTX 3050 nvidia · entry · 8GB | D | 263 | Estimated |
| 65 | NVIDIA GeForce GTX 1660 Super nvidia · mid · 6GB | D | 261 | Estimated |
| 66 | ASUS ROG Strix Scar 18 (RTX 5090 Mobile) nvidia · enthusiast · 24GB | D | 259 | Estimated |
| 67 | Razer Blade 16 (2025, RTX 5090 Mobile) nvidia · enthusiast · 24GB | D | 259 | Estimated |
| 68 | NVIDIA GeForce RTX 2060 nvidia · mid · 6GB | D | 257 | Estimated |
| 69 | NVIDIA GeForce GTX 1660 Ti nvidia · mid · 6GB | D | 247 | Estimated |
| 70 | Lenovo Legion 5 Pro Gen 7 (RTX 3080 16GB) nvidia · high · 16GB | D | 238 | Estimated |
| 71 | NVIDIA GeForce RTX 3050 Ti (Mobile) nvidia · mobile · 4GB | D | 224 | Estimated |
| 72 | NVIDIA GeForce GTX 1650 Super nvidia · entry · 4GB | D | 221 | Estimated |
| 73 | NVIDIA GeForce GTX 1660 nvidia · mid · 6GB | D | 218 | Estimated |
| 74 | NVIDIA GeForce GTX 1060 3GB nvidia · entry · 3GB | D | 218 | Estimated |
| 75 | NVIDIA GeForce GTX 1060 6GB nvidia · entry · 6GB | D | 218 | Estimated |
| 76 | ASUS Ascent GX10 (NVIDIA GB10) nvidia · workstation | D | 217 | Estimated |
| 77 | NVIDIA GeForce GTX 1650 nvidia · entry · 4GB | D | 204 | Estimated |
| 78 | NVIDIA GeForce GTX 1050 Ti nvidia · entry · 4GB | D | 198 | Estimated |
| 79 | NVIDIA DGX Spark (Project Digits) nvidia · workstation | D | 140 | 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.