NVIDIA GeForce RTX 5090
Full GPU32 GB VRAM
Estimated speed: ~2048 tok/s
Bandwidth: 1792 GB/s
Loading GPU recommendations...
Running compatibility calculations across available GPUs.
Loading GPU recommendations...
Running compatibility calculations across available GPUs.
GPU Recommendations
Comparing 90 GPUs for running Gemma 3 1B (Q4_K_M, 0.7 GB).
Ranking priority: compatibility verdict first, then estimated speed, then memory bandwidth. Buying links are optional shortcuts if you are ready to upgrade.
Copy a link to this GPU ranking so someone else can see the best upgrade paths for Gemma 3 1B.
32 GB VRAM
Estimated speed: ~2048 tok/s
Bandwidth: 1792 GB/s
256 GB VRAM
Estimated speed: ~1248 tok/s
Bandwidth: 1092 GB/s
24 GB VRAM
Estimated speed: ~1152 tok/s
Bandwidth: 1008 GB/s
24 GB VRAM
Estimated speed: ~1152 tok/s
Bandwidth: 1008 GB/s
16 GB VRAM
Estimated speed: ~1097.1 tok/s
Bandwidth: 960 GB/s
24 GB VRAM
Estimated speed: ~1097.1 tok/s
Bandwidth: 960 GB/s
24 GB VRAM
Estimated speed: ~1069.7 tok/s
Bandwidth: 936 GB/s
12 GB VRAM
Estimated speed: ~1042.3 tok/s
Bandwidth: 912 GB/s
12 GB VRAM
Estimated speed: ~1042.3 tok/s
Bandwidth: 912 GB/s
16 GB VRAM
Estimated speed: ~1024 tok/s
Bandwidth: 896 GB/s
20 GB VRAM
Estimated speed: ~914.3 tok/s
Bandwidth: 800 GB/s
128 GB VRAM
Estimated speed: ~914.3 tok/s
Bandwidth: 800 GB/s
192 GB VRAM
Estimated speed: ~914.3 tok/s
Bandwidth: 800 GB/s
192 GB VRAM
Estimated speed: ~914.3 tok/s
Bandwidth: 800 GB/s
10 GB VRAM
Estimated speed: ~868.6 tok/s
Bandwidth: 760 GB/s
16 GB VRAM
Estimated speed: ~841.1 tok/s
Bandwidth: 736 GB/s
16 GB VRAM
Estimated speed: ~819.4 tok/s
Bandwidth: 717 GB/s
12 GB VRAM
Estimated speed: ~768 tok/s
Bandwidth: 672 GB/s
16 GB VRAM
Estimated speed: ~768 tok/s
Bandwidth: 672 GB/s
16 GB VRAM
Estimated speed: ~713.1 tok/s
Bandwidth: 624 GB/s
11 GB VRAM
Estimated speed: ~704 tok/s
Bandwidth: 616 GB/s
8 GB VRAM
Estimated speed: ~694.9 tok/s
Bandwidth: 608 GB/s
16 GB VRAM
Estimated speed: ~658.3 tok/s
Bandwidth: 576 GB/s
16 GB VRAM
Estimated speed: ~658.3 tok/s
Bandwidth: 576 GB/s
16 GB VRAM
Estimated speed: ~658.3 tok/s
Bandwidth: 576 GB/s
16 GB VRAM
Estimated speed: ~640 tok/s
Bandwidth: 560 GB/s
128 GB VRAM
Estimated speed: ~624 tok/s
Bandwidth: 546 GB/s
16 GB VRAM
Estimated speed: ~585.1 tok/s
Bandwidth: 512 GB/s
16 GB VRAM
Estimated speed: ~585.1 tok/s
Bandwidth: 512 GB/s
16 GB VRAM
Estimated speed: ~585.1 tok/s
Bandwidth: 512 GB/s
8 GB VRAM
Estimated speed: ~585.1 tok/s
Bandwidth: 512 GB/s
8 GB VRAM
Estimated speed: ~585.1 tok/s
Bandwidth: 512 GB/s
8 GB VRAM
Estimated speed: ~585.1 tok/s
Bandwidth: 512 GB/s
12 GB VRAM
Estimated speed: ~576 tok/s
Bandwidth: 504 GB/s
12 GB VRAM
Estimated speed: ~576 tok/s
Bandwidth: 504 GB/s
12 GB VRAM
Estimated speed: ~576 tok/s
Bandwidth: 504 GB/s
8 GB VRAM
Estimated speed: ~566.9 tok/s
Bandwidth: 496 GB/s
11 GB VRAM
Estimated speed: ~553.1 tok/s
Bandwidth: 484 GB/s
12 GB VRAM
Estimated speed: ~521.1 tok/s
Bandwidth: 456 GB/s
8 GB VRAM
Estimated speed: ~512 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~512 tok/s
Bandwidth: 448 GB/s
16 GB VRAM
Estimated speed: ~512 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~512 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~512 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~512 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~512 tok/s
Bandwidth: 448 GB/s
12 GB VRAM
Estimated speed: ~493.7 tok/s
Bandwidth: 432 GB/s
12 GB VRAM
Estimated speed: ~493.7 tok/s
Bandwidth: 432 GB/s
12 GB VRAM
Estimated speed: ~493.7 tok/s
Bandwidth: 432 GB/s
64 GB VRAM
Estimated speed: ~457.1 tok/s
Bandwidth: 400 GB/s
96 GB VRAM
Estimated speed: ~457.1 tok/s
Bandwidth: 400 GB/s
128 GB VRAM
Estimated speed: ~457.1 tok/s
Bandwidth: 400 GB/s
8 GB VRAM
Estimated speed: ~438.9 tok/s
Bandwidth: 384 GB/s
12 GB VRAM
Estimated speed: ~438.9 tok/s
Bandwidth: 384 GB/s
12 GB VRAM
Estimated speed: ~411.4 tok/s
Bandwidth: 360 GB/s
6 GB VRAM
Estimated speed: ~384 tok/s
Bandwidth: 336 GB/s
6 GB VRAM
Estimated speed: ~384 tok/s
Bandwidth: 336 GB/s
6 GB VRAM
Estimated speed: ~384 tok/s
Bandwidth: 336 GB/s
8 GB VRAM
Estimated speed: ~365.7 tok/s
Bandwidth: 320 GB/s
16 GB VRAM
Estimated speed: ~329.1 tok/s
Bandwidth: 288 GB/s
8 GB VRAM
Estimated speed: ~329.1 tok/s
Bandwidth: 288 GB/s
6 GB VRAM
Estimated speed: ~329.1 tok/s
Bandwidth: 288 GB/s
16 GB VRAM
Estimated speed: ~329.1 tok/s
Bandwidth: 288 GB/s
8 GB VRAM
Estimated speed: ~329.1 tok/s
Bandwidth: 288 GB/s
8 GB VRAM
Estimated speed: ~329.1 tok/s
Bandwidth: 288 GB/s
8 GB VRAM
Estimated speed: ~320 tok/s
Bandwidth: 280 GB/s
48 GB VRAM
Estimated speed: ~312 tok/s
Bandwidth: 273 GB/s
8 GB VRAM
Estimated speed: ~310.9 tok/s
Bandwidth: 272 GB/s
8 GB VRAM
Estimated speed: ~292.6 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~292.6 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~292.6 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~292.6 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~292.6 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~256 tok/s
Bandwidth: 224 GB/s
8 GB VRAM
Estimated speed: ~256 tok/s
Bandwidth: 224 GB/s
32 GB VRAM
Estimated speed: ~228.6 tok/s
Bandwidth: 200 GB/s
32 GB VRAM
Estimated speed: ~228.6 tok/s
Bandwidth: 200 GB/s
32 GB VRAM
Estimated speed: ~228.6 tok/s
Bandwidth: 200 GB/s
6 GB VRAM
Estimated speed: ~219.4 tok/s
Bandwidth: 192 GB/s
6 GB VRAM
Estimated speed: ~219.4 tok/s
Bandwidth: 192 GB/s
4 GB VRAM
Estimated speed: ~219.4 tok/s
Bandwidth: 192 GB/s
6 GB VRAM
Estimated speed: ~219.4 tok/s
Bandwidth: 192 GB/s
3 GB VRAM
Estimated speed: ~219.4 tok/s
Bandwidth: 192 GB/s
36 GB VRAM
Estimated speed: ~171.4 tok/s
Bandwidth: 150 GB/s
4 GB VRAM
Estimated speed: ~146.3 tok/s
Bandwidth: 128 GB/s
32 GB VRAM
Estimated speed: ~137.1 tok/s
Bandwidth: 120 GB/s
4 GB VRAM
Estimated speed: ~128 tok/s
Bandwidth: 112 GB/s
24 GB VRAM
Estimated speed: ~114.3 tok/s
Bandwidth: 100 GB/s
24 GB VRAM
Estimated speed: ~114.3 tok/s
Bandwidth: 100 GB/s
16 GB VRAM
Estimated speed: ~77.7 tok/s
Bandwidth: 68 GB/s
| GPU | VRAM | Verdict | Estimated tok/s | Bandwidth | Where to Buy |
|---|---|---|---|---|---|
| NVIDIA GeForce RTX 5090 | 32 GB | Full GPU | ~2048 | 1792 GB/s | |
| Apple M4 Ultra | 256 GB | Full GPU | ~1248 | 1092 GB/s | |
| NVIDIA GeForce RTX 4090 | 24 GB | Full GPU | ~1152 | 1008 GB/s | |
| NVIDIA GeForce RTX 3090 Ti | 24 GB | Full GPU | ~1152 | 1008 GB/s | |
| NVIDIA GeForce RTX 5080 | 16 GB | Full GPU | ~1097.1 | 960 GB/s | |
| AMD Radeon RX 7900 XTX | 24 GB | Full GPU | ~1097.1 | 960 GB/s | |
| NVIDIA GeForce RTX 3090 | 24 GB | Full GPU | ~1069.7 | 936 GB/s | |
| NVIDIA GeForce RTX 3080 Ti | 12 GB | Full GPU | ~1042.3 | 912 GB/s | |
| NVIDIA GeForce RTX 3080 12GB | 12 GB | Full GPU | ~1042.3 | 912 GB/s | |
| NVIDIA GeForce RTX 5070 Ti | 16 GB | Full GPU | ~1024 | 896 GB/s | |
| AMD Radeon RX 7900 XT | 20 GB | Full GPU | ~914.3 | 800 GB/s | |
| Apple M1 Ultra | 128 GB | Full GPU | ~914.3 | 800 GB/s | |
| Apple M2 Ultra | 192 GB | Full GPU | ~914.3 | 800 GB/s | |
| Apple M3 Ultra | 192 GB | Full GPU | ~914.3 | 800 GB/s | |
| NVIDIA GeForce RTX 3080 10GB | 10 GB | Full GPU | ~868.6 | 760 GB/s | |
| NVIDIA GeForce RTX 4080 Super | 16 GB | Full GPU | ~841.1 | 736 GB/s | |
| NVIDIA GeForce RTX 4080 | 16 GB | Full GPU | ~819.4 | 717 GB/s | |
| NVIDIA GeForce RTX 5070 | 12 GB | Full GPU | ~768 | 672 GB/s | |
| NVIDIA GeForce RTX 4070 Ti Super | 16 GB | Full GPU | ~768 | 672 GB/s | |
| AMD Radeon RX 7800 XT | 16 GB | Full GPU | ~713.1 | 624 GB/s | |
| NVIDIA GeForce RTX 2080 Ti | 11 GB | Full GPU | ~704 | 616 GB/s | |
| NVIDIA GeForce RTX 3070 Ti | 8 GB | Full GPU | ~694.9 | 608 GB/s | |
| NVIDIA GeForce RTX 4090 Laptop | 16 GB | Full GPU | ~658.3 | 576 GB/s | |
| AMD Radeon RX 7900 GRE | 16 GB | Full GPU | ~658.3 | 576 GB/s | |
| AMD Radeon RX 6950 XT | 16 GB | Full GPU | ~658.3 | 576 GB/s | |
| Intel Arc A770 16GB | 16 GB | Full GPU | ~640 | 560 GB/s | |
| Apple M4 Max | 128 GB | Full GPU | ~624 | 546 GB/s | |
| AMD Radeon RX 6900 XT | 16 GB | Full GPU | ~585.1 | 512 GB/s | |
| AMD Radeon RX 6800 XT | 16 GB | Full GPU | ~585.1 | 512 GB/s | |
| AMD Radeon RX 6800 | 16 GB | Full GPU | ~585.1 | 512 GB/s | |
| Intel Arc A770 8GB | 8 GB | Full GPU | ~585.1 | 512 GB/s | |
| Intel Arc A750 | 8 GB | Full GPU | ~585.1 | 512 GB/s | |
| Intel Arc A580 | 8 GB | Full GPU | ~585.1 | 512 GB/s | |
| NVIDIA GeForce RTX 4070 Ti | 12 GB | Full GPU | ~576 | 504 GB/s | |
| NVIDIA GeForce RTX 4070 Super | 12 GB | Full GPU | ~576 | 504 GB/s | |
| NVIDIA GeForce RTX 4070 | 12 GB | Full GPU | ~576 | 504 GB/s | |
| NVIDIA GeForce RTX 2080 Super | 8 GB | Full GPU | ~566.9 | 496 GB/s | |
| NVIDIA GeForce GTX 1080 Ti | 11 GB | Full GPU | ~553.1 | 484 GB/s | |
| Intel Arc B580 | 12 GB | Full GPU | ~521.1 | 456 GB/s | |
| NVIDIA GeForce RTX 3070 | 8 GB | Full GPU | ~512 | 448 GB/s | |
| NVIDIA GeForce RTX 3060 Ti | 8 GB | Full GPU | ~512 | 448 GB/s | |
| NVIDIA GeForce RTX 3080 Laptop | 16 GB | Full GPU | ~512 | 448 GB/s | |
| NVIDIA GeForce RTX 2080 | 8 GB | Full GPU | ~512 | 448 GB/s | |
| NVIDIA GeForce RTX 2070 Super | 8 GB | Full GPU | ~512 | 448 GB/s | |
| NVIDIA GeForce RTX 2070 | 8 GB | Full GPU | ~512 | 448 GB/s | |
| NVIDIA GeForce RTX 2060 Super | 8 GB | Full GPU | ~512 | 448 GB/s | |
| NVIDIA GeForce RTX 4080 Laptop | 12 GB | Full GPU | ~493.7 | 432 GB/s | |
| AMD Radeon RX 7700 XT | 12 GB | Full GPU | ~493.7 | 432 GB/s | |
| AMD Radeon RX 6750 XT | 12 GB | Full GPU | ~493.7 | 432 GB/s | |
| Apple M1 Max | 64 GB | Full GPU | ~457.1 | 400 GB/s | |
| Apple M2 Max | 96 GB | Full GPU | ~457.1 | 400 GB/s | |
| Apple M3 Max | 128 GB | Full GPU | ~457.1 | 400 GB/s | |
| NVIDIA GeForce RTX 3070 Laptop | 8 GB | Full GPU | ~438.9 | 384 GB/s | |
| AMD Radeon RX 6700 XT | 12 GB | Full GPU | ~438.9 | 384 GB/s | |
| NVIDIA GeForce RTX 3060 | 12 GB | Full GPU | ~411.4 | 360 GB/s | |
| NVIDIA GeForce RTX 3060 Laptop | 6 GB | Full GPU | ~384 | 336 GB/s | |
| NVIDIA GeForce RTX 2060 | 6 GB | Full GPU | ~384 | 336 GB/s | |
| NVIDIA GeForce GTX 1660 Super | 6 GB | Full GPU | ~384 | 336 GB/s | |
| NVIDIA GeForce GTX 1080 | 8 GB | Full GPU | ~365.7 | 320 GB/s | |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16 GB | Full GPU | ~329.1 | 288 GB/s | |
| NVIDIA GeForce RTX 4060 Ti 8GB | 8 GB | Full GPU | ~329.1 | 288 GB/s | |
| NVIDIA GeForce GTX 1660 Ti | 6 GB | Full GPU | ~329.1 | 288 GB/s | |
| AMD Radeon RX 7600 XT | 16 GB | Full GPU | ~329.1 | 288 GB/s | |
| AMD Radeon RX 7600 | 8 GB | Full GPU | ~329.1 | 288 GB/s | |
| AMD Radeon RX 7600M XT | 8 GB | Full GPU | ~329.1 | 288 GB/s | |
| AMD Radeon RX 6650 XT | 8 GB | Full GPU | ~320 | 280 GB/s | |
| Apple M4 Pro | 48 GB | Full GPU | ~312 | 273 GB/s | |
| NVIDIA GeForce RTX 4060 | 8 GB | Full GPU | ~310.9 | 272 GB/s | |
| NVIDIA GeForce RTX 4070 Laptop | 8 GB | Full GPU | ~292.6 | 256 GB/s | |
| NVIDIA GeForce RTX 4060 Laptop | 8 GB | Full GPU | ~292.6 | 256 GB/s | |
| NVIDIA GeForce GTX 1070 Ti | 8 GB | Full GPU | ~292.6 | 256 GB/s | |
| NVIDIA GeForce GTX 1070 | 8 GB | Full GPU | ~292.6 | 256 GB/s | |
| AMD Radeon RX 6600 XT | 8 GB | Full GPU | ~292.6 | 256 GB/s | |
| NVIDIA GeForce RTX 3050 | 8 GB | Full GPU | ~256 | 224 GB/s | |
| AMD Radeon RX 6600 | 8 GB | Full GPU | ~256 | 224 GB/s | |
| Apple M1 Pro (10-core GPU) | 32 GB | Full GPU | ~228.6 | 200 GB/s | |
| Apple M1 Pro (16-core GPU) | 32 GB | Full GPU | ~228.6 | 200 GB/s | |
| Apple M2 Pro | 32 GB | Full GPU | ~228.6 | 200 GB/s | |
| NVIDIA GeForce RTX 4050 Laptop | 6 GB | Full GPU | ~219.4 | 192 GB/s | |
| NVIDIA GeForce GTX 1660 | 6 GB | Full GPU | ~219.4 | 192 GB/s | |
| NVIDIA GeForce GTX 1650 Super | 4 GB | Full GPU | ~219.4 | 192 GB/s | |
| NVIDIA GeForce GTX 1060 6GB | 6 GB | Full GPU | ~219.4 | 192 GB/s | |
| NVIDIA GeForce GTX 1060 3GB | 3 GB | Full GPU | ~219.4 | 192 GB/s | |
| Apple M3 Pro | 36 GB | Full GPU | ~171.4 | 150 GB/s | |
| NVIDIA GeForce GTX 1650 | 4 GB | Full GPU | ~146.3 | 128 GB/s | |
| Apple M4 | 32 GB | Full GPU | ~137.1 | 120 GB/s | |
| NVIDIA GeForce GTX 1050 Ti | 4 GB | Full GPU | ~128 | 112 GB/s | |
| Apple M2 | 24 GB | Full GPU | ~114.3 | 100 GB/s | |
| Apple M3 | 24 GB | Full GPU | ~114.3 | 100 GB/s | |
| Apple M1 | 16 GB | Full GPU | ~77.7 | 68 GB/s |