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
152 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 | AMD Instinct MI355X amd · workstation · 288GB | B | 626 | Estimated |
| 15 | AMD Instinct MI350X amd · workstation · 288GB | B | 626 | Estimated |
| 16 | AMD Instinct MI300X amd · workstation · 192GB | B | 621 | Estimated |
| 17 | AMD Instinct MI300A (APU) amd · workstation · 128GB | B | 620 | Estimated |
| 18 | Apple M4 Ultra apple · enthusiast | B | 615 | Estimated |
| 19 | AMD Instinct MI325X amd · workstation · 256GB | B | 615 | Estimated |
| 20 | AMD Instinct MI250X amd · workstation · 128GB | B | 614 | Estimated |
| 21 | AMD Instinct MI210 amd · workstation · 64GB | B | 587 | Estimated |
| 22 | Intel Gaudi 2 intel · workstation · 96GB | B | 536 | Estimated |
| 23 | Intel Gaudi 3 intel · workstation · 128GB | B | 536 | Estimated |
| 24 | NVIDIA RTX 4090 48GB (China-mod) nvidia · workstation · 48GB | B | 534 | Estimated |
| 25 | Apple M1 Ultra apple · enthusiast | B | 529 | Estimated |
| 26 | NVIDIA RTX 5000 PRO Blackwell 48GB nvidia · workstation · 48GB | B | 529 | Estimated |
| 27 | NVIDIA RTX 6000 Ada Generation nvidia · workstation · 48GB | B | 529 | Estimated |
| 28 | Apple M3 Ultra apple · enthusiast | B | 522 | Estimated |
| 29 | Apple M2 Ultra apple · enthusiast | B | 522 | Estimated |
| 30 | NVIDIA GeForce RTX 3090 Ti nvidia · enthusiast · 24GB | B | 520 | Estimated |
| 31 | NVIDIA GeForce RTX 4090 nvidia · enthusiast · 24GB | B | 520 | Estimated |
| 32 | NVIDIA GeForce RTX 5090 Mobile nvidia · enthusiast · 24GB | B | 512 | Estimated |
| 33 | Apple Mac Studio (M3 Ultra) apple · enthusiast | B | 512 | Estimated |
| 34 | NVIDIA RTX PRO 4500 Blackwell nvidia · workstation · 32GB | B | 507 | Estimated |
| 35 | NVIDIA GeForce RTX 3090 nvidia · enthusiast · 24GB | B | 505 | Estimated |
| 36 | NVIDIA L40 nvidia · workstation · 48GB | B | 503 | Estimated |
| 37 | NVIDIA L40S nvidia · workstation · 48GB | B | 500 | Estimated |
| 38 | NVIDIA RTX A6000 (Ampere) nvidia · workstation · 48GB | C | 477 | Estimated |
| 39 | NVIDIA GeForce RTX 5070 Ti nvidia · high · 16GB | C | 477 | Estimated |
| 40 | NVIDIA RTX A5000 nvidia · workstation · 24GB | C | 468 | Estimated |
| 41 | NVIDIA A40 nvidia · workstation · 48GB | C | 458 | Estimated |
| 42 | Apple M4 Max apple · enthusiast | C | 457 | Estimated |
| 43 | NVIDIA GeForce RTX 3080 Ti nvidia · enthusiast · 12GB | C | 456 | Estimated |
| 44 | NVIDIA GeForce RTX 3080 12GB nvidia · high · 12GB | C | 456 | Estimated |
| 45 | NVIDIA RTX PRO 4000 Blackwell nvidia · workstation · 24GB | C | 455 | Estimated |
| 46 | MacBook Pro 16" M4 Max apple · enthusiast | C | 445 | Estimated |
| 47 | Apple Mac Studio (M4 Max) apple · enthusiast | C | 438 | Estimated |
| 48 | NVIDIA GeForce RTX 4080 Super nvidia · high · 16GB | C | 433 | Estimated |
| 49 | NVIDIA GeForce RTX 4080 nvidia · high · 16GB | C | 428 | Estimated |
| 50 | AMD Radeon RX 7900 XTX amd · enthusiast · 24GB | C | 420 | Estimated |
| 51 | NVIDIA GeForce RTX 4070 Ti Super nvidia · high · 16GB | C | 418 | Estimated |
| 52 | NVIDIA RTX 5000 Ada Generation nvidia · workstation · 32GB | C | 414 | Estimated |
| 53 | NVIDIA RTX 2080 Ti 22GB (China-mod) nvidia · mid · 22GB | C | 405 | Estimated |
| 54 | Apple M1 Max apple · high | C | 404 | Estimated |
| 55 | Apple M2 Max apple · high | C | 400 | Estimated |
| 56 | NVIDIA GeForce RTX 4090 Mobile nvidia · enthusiast · 16GB | C | 400 | Estimated |
| 57 | NVIDIA GeForce RTX 5070 nvidia · mid · 12GB | C | 399 | Estimated |
| 58 | Apple M3 Max apple · enthusiast | C | 398 | Estimated |
| 59 | NVIDIA GeForce RTX 3080 10GB nvidia · high · 10GB | C | 397 | Estimated |
| 60 | AMD Radeon RX 7900 XT amd · enthusiast · 20GB | C | 365 | Estimated |
| 61 | NVIDIA GeForce RTX 5060 Ti 16GB nvidia · mid · 16GB | C | 364 | Estimated |
| 62 | NVIDIA GeForce RTX 2080 Ti nvidia · enthusiast · 11GB | C | 363 | Estimated |
| 63 | NVIDIA L4 nvidia · workstation · 24GB | C | 360 | Estimated |
| 64 | NVIDIA GeForce RTX 3070 Ti nvidia · high · 8GB | C | 358 | Estimated |
| 65 | NVIDIA GeForce RTX 4070 nvidia · mid · 12GB | C | 356 | Estimated |
| 66 | NVIDIA GeForce RTX 4070 Super nvidia · mid · 12GB | C | 355 | Estimated |
| 67 | Apple M4 Pro apple · high | C | 351 | Estimated |
| 68 | NVIDIA GeForce RTX 4070 Ti nvidia · high · 12GB | C | 351 | Estimated |
| 69 | Apple Mac Mini (M4 Pro) apple · high | C | 340 | Estimated |
| 70 | AMD Radeon RX 9060 XT amd · mid · 16GB | C | 339 | Estimated |
| 71 | NVIDIA GeForce RTX 5070 Laptop GPU nvidia · high · 12GB | C | 337 | Estimated |
| 72 | AMD Radeon RX 9070 XT amd · high · 16GB | C | 332 | Estimated |
| 73 | AMD Radeon RX 9070 amd · high · 16GB | C | 332 | Estimated |
| 74 | NVIDIA GeForce RTX 2080 Super nvidia · high · 8GB | C | 330 | Estimated |
| 75 | AMD Radeon RX 7800 XT amd · high · 16GB | C | 329 | Estimated |
| 76 | NVIDIA GeForce GTX 1080 Ti nvidia · high · 11GB | C | 327 | Estimated |
| 77 | NVIDIA GeForce RTX 5060 nvidia · entry · 8GB | C | 326 | Estimated |
| 78 | NVIDIA GeForce RTX 2070 nvidia · high · 8GB | C | 323 | Estimated |
| 79 | NVIDIA GeForce RTX 2060 Super nvidia · mid · 8GB | C | 323 | Estimated |
| 80 | NVIDIA GeForce RTX 5060 Ti 8GB nvidia · mid · 8GB | C | 322 | Estimated |
| 81 | NVIDIA GeForce RTX 3060 Ti nvidia · high · 8GB | C | 321 | Estimated |
| 82 | NVIDIA GeForce RTX 4060 Ti 16GB nvidia · mid · 16GB | C | 320 | Estimated |
| 83 | NVIDIA GeForce RTX 3060 12GB nvidia · mid · 12GB | C | 319 | Estimated |
| 84 | NVIDIA GeForce RTX 3070 nvidia · mid · 8GB | C | 319 | Estimated |
| 85 | AMD Radeon RX 7900 GRE amd · high · 16GB | C | 319 | Estimated |
| 86 | NVIDIA GeForce RTX 2070 Super nvidia · high · 8GB | C | 319 | Estimated |
| 87 | AMD Radeon RX 6950 XT amd · enthusiast · 16GB | C | 316 | Estimated |
| 88 | AMD Radeon RX 6800 amd · high · 16GB | C | 304 | Estimated |
| 89 | AMD Radeon RX 6800 XT amd · enthusiast · 16GB | C | 302 | Estimated |
| 90 | AMD Radeon RX 6900 XT amd · enthusiast · 16GB | C | 302 | Estimated |
| 91 | NVIDIA GeForce RTX 5050 nvidia · entry · 8GB | D | 291 | Estimated |
| 92 | AMD Ryzen AI Max+ 395 (Strix Halo) amd · workstation | D | 288 | Estimated |
| 93 | NVIDIA GeForce GTX 1080 nvidia · mid · 8GB | D | 286 | Estimated |
| 94 | NVIDIA GeForce RTX 4060 nvidia · entry · 8GB | D | 279 | Estimated |
| 95 | NVIDIA GeForce RTX 4060 Ti 8GB nvidia · mid · 8GB | D | 278 | Estimated |
| 96 | NVIDIA GeForce GTX 1070 nvidia · mid · 8GB | D | 270 | Estimated |
| 97 | NVIDIA GeForce GTX 1070 Ti nvidia · mid · 8GB | D | 268 | Estimated |
| 98 | AMD Radeon RX 9070 GRE amd · high · 12GB | D | 267 | Estimated |
| 99 | AMD Radeon RX 7700 XT amd · mid · 12GB | D | 265 | Estimated |
| 100 | AMD Radeon RX 6750 XT amd · high · 12GB | D | 265 | Estimated |
| 101 | NVIDIA GeForce RTX 3050 nvidia · entry · 8GB | D | 263 | Estimated |
| 102 | Apple MacBook Air (M4) apple · mid | D | 262 | Estimated |
| 103 | NVIDIA GeForce GTX 1660 Super nvidia · mid · 6GB | D | 261 | Estimated |
| 104 | Intel Arc Pro B60 24GB intel · workstation · 24GB | D | 260 | Estimated |
| 105 | ASUS ROG Strix Scar 18 (RTX 5090 Mobile) nvidia · enthusiast · 24GB | D | 259 | Estimated |
| 106 | Razer Blade 16 (2025, RTX 5090 Mobile) nvidia · enthusiast · 24GB | D | 259 | Estimated |
| 107 | NVIDIA GeForce RTX 2060 nvidia · mid · 6GB | D | 257 | Estimated |
| 108 | Intel Arc A770 16GB intel · mid · 16GB | D | 256 | Estimated |
| 109 | AMD Radeon RX 7600 XT amd · mid · 16GB | D | 256 | Estimated |
| 110 | AMD Radeon RX 6700 XT amd · high · 12GB | D | 255 | Estimated |
| 111 | NVIDIA GeForce GTX 1660 Ti nvidia · mid · 6GB | D | 247 | Estimated |
| 112 | AMD Ryzen AI 9 HX 370 (Strix Point) amd · pc-npu | D | 246 | Estimated |
| 113 | Apple Mac Mini (M4) apple · mid | D | 245 | Estimated |
| 114 | Apple M4 (iPad Pro) apple · mobile | D | 244 | Estimated |
| 115 | Lenovo Legion 5 Pro Gen 7 (RTX 3080 16GB) nvidia · high · 16GB | D | 238 | Estimated |
| 116 | Apple A18 Pro apple · mobile | D | 227 | Estimated |
| 117 | Apple A17 Pro apple · mobile | D | 225 | Estimated |
| 118 | NVIDIA GeForce RTX 3050 Ti (Mobile) nvidia · mobile · 4GB | D | 224 | Estimated |
| 119 | NVIDIA GeForce GTX 1650 Super nvidia · entry · 4GB | D | 221 | Estimated |
| 120 | Intel Arc B580 intel · mid · 12GB | D | 218 | Estimated |
| 121 | NVIDIA GeForce GTX 1660 nvidia · mid · 6GB | D | 218 | Estimated |
| 122 | NVIDIA GeForce GTX 1060 3GB nvidia · entry · 3GB | D | 218 | Estimated |
| 123 | NVIDIA GeForce GTX 1060 6GB nvidia · entry · 6GB | D | 218 | Estimated |
| 124 | ASUS Ascent GX10 (NVIDIA GB10) nvidia · workstation | D | 217 | Estimated |
| 125 | AMD Radeon RX 5700 XT amd · high · 8GB | D | 214 | Estimated |
| 126 | AMD Radeon RX 6650 XT amd · mid · 8GB | D | 212 | Estimated |
| 127 | AMD Radeon RX 6600 XT amd · mid · 8GB | D | 208 | Estimated |
| 128 | NVIDIA GeForce GTX 1650 nvidia · entry · 4GB | D | 204 | Estimated |
| 129 | Qualcomm Snapdragon 8 Elite qualcomm · mobile | D | 204 | Estimated |
| 130 | AMD Radeon RX 6600 amd · mid · 8GB | D | 202 | Estimated |
| 131 | NVIDIA GeForce GTX 1050 Ti nvidia · entry · 4GB | D | 198 | Estimated |
| 132 | Intel Arc B570 intel · mid · 10GB | D | 185 | Estimated |
| 133 | Qualcomm Snapdragon 8 Gen 3 qualcomm · mobile | D | 179 | Estimated |
| 134 | Intel Core Ultra 7 258V (Lunar Lake) intel · pc-npu | D | 177 | Estimated |
| 135 | Intel Core Ultra 300 (Panther Lake) intel · pc-npu | D | 175 | Estimated |
| 136 | AMD Radeon RX 580 8GB amd · mid · 8GB | D | 172 | Estimated |
| 137 | AMD Radeon RX 5500 XT 8GB amd · entry · 8GB | D | 167 | Estimated |
| 138 | Google Tensor G4 google · mobile | D | 162 | Estimated |
| 139 | Qualcomm Snapdragon X2 Elite qualcomm · pc-npu | D | 161 | Estimated |
| 140 | AMD EPYC 9005 (Zen 5, Turin) amd · workstation | D | 161 | Estimated |
| 141 | AMD Radeon RX 5600 XT amd · mid · 6GB | D | 158 | Estimated |
| 142 | HP ZBook Ultra G1a (Ryzen AI Max+ PRO 395) amd · workstation | D | 155 | Estimated |
| 143 | Framework Desktop (Ryzen AI Max+ 395) amd · workstation | D | 153 | Estimated |
| 144 | GMKtec EVO-X2 (Ryzen AI Max+ 395) amd · workstation | D | 153 | Estimated |
| 145 | Framework Laptop 16 (RX 7700S) amd · mid · 8GB | D | 147 | Estimated |
| 146 | NVIDIA DGX Spark (Project Digits) nvidia · workstation | D | 140 | Estimated |
| 147 | AMD Radeon 880M (Strix Point iGPU) amd · entry | D | 132 | Estimated |
| 148 | AMD Radeon RX 570 amd · entry · 4GB | D | 131 | Estimated |
| 149 | AMD Radeon 780M (Phoenix iGPU) amd · entry | D | 127 | Estimated |
| 150 | Intel Arc 140V (Lunar Lake iGPU) intel · entry | D | 115 | Estimated |
| 151 | Qualcomm Snapdragon X Elite qualcomm · high | D | 28 | Estimated |
| 152 | Qualcomm Snapdragon X Plus qualcomm · mid | D | 28 | 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.