NVIDIA GeForce RTX 5090
Full GPU32 GB VRAM
Estimated speed: ~796.4 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 Stable Code 3B (Q4_K_M, 1.8 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 Stable Code 3B.
32 GB VRAM
Estimated speed: ~796.4 tok/s
Bandwidth: 1792 GB/s
256 GB VRAM
Estimated speed: ~485.3 tok/s
Bandwidth: 1092 GB/s
24 GB VRAM
Estimated speed: ~448 tok/s
Bandwidth: 1008 GB/s
24 GB VRAM
Estimated speed: ~448 tok/s
Bandwidth: 1008 GB/s
16 GB VRAM
Estimated speed: ~426.7 tok/s
Bandwidth: 960 GB/s
24 GB VRAM
Estimated speed: ~426.7 tok/s
Bandwidth: 960 GB/s
24 GB VRAM
Estimated speed: ~416 tok/s
Bandwidth: 936 GB/s
12 GB VRAM
Estimated speed: ~405.3 tok/s
Bandwidth: 912 GB/s
12 GB VRAM
Estimated speed: ~405.3 tok/s
Bandwidth: 912 GB/s
16 GB VRAM
Estimated speed: ~398.2 tok/s
Bandwidth: 896 GB/s
20 GB VRAM
Estimated speed: ~355.6 tok/s
Bandwidth: 800 GB/s
128 GB VRAM
Estimated speed: ~355.6 tok/s
Bandwidth: 800 GB/s
192 GB VRAM
Estimated speed: ~355.6 tok/s
Bandwidth: 800 GB/s
192 GB VRAM
Estimated speed: ~355.6 tok/s
Bandwidth: 800 GB/s
10 GB VRAM
Estimated speed: ~337.8 tok/s
Bandwidth: 760 GB/s
16 GB VRAM
Estimated speed: ~327.1 tok/s
Bandwidth: 736 GB/s
16 GB VRAM
Estimated speed: ~318.7 tok/s
Bandwidth: 717 GB/s
12 GB VRAM
Estimated speed: ~298.7 tok/s
Bandwidth: 672 GB/s
16 GB VRAM
Estimated speed: ~298.7 tok/s
Bandwidth: 672 GB/s
16 GB VRAM
Estimated speed: ~277.3 tok/s
Bandwidth: 624 GB/s
11 GB VRAM
Estimated speed: ~273.8 tok/s
Bandwidth: 616 GB/s
8 GB VRAM
Estimated speed: ~270.2 tok/s
Bandwidth: 608 GB/s
16 GB VRAM
Estimated speed: ~256 tok/s
Bandwidth: 576 GB/s
16 GB VRAM
Estimated speed: ~256 tok/s
Bandwidth: 576 GB/s
16 GB VRAM
Estimated speed: ~256 tok/s
Bandwidth: 576 GB/s
16 GB VRAM
Estimated speed: ~248.9 tok/s
Bandwidth: 560 GB/s
128 GB VRAM
Estimated speed: ~242.7 tok/s
Bandwidth: 546 GB/s
16 GB VRAM
Estimated speed: ~227.6 tok/s
Bandwidth: 512 GB/s
16 GB VRAM
Estimated speed: ~227.6 tok/s
Bandwidth: 512 GB/s
16 GB VRAM
Estimated speed: ~227.6 tok/s
Bandwidth: 512 GB/s
8 GB VRAM
Estimated speed: ~227.6 tok/s
Bandwidth: 512 GB/s
8 GB VRAM
Estimated speed: ~227.6 tok/s
Bandwidth: 512 GB/s
8 GB VRAM
Estimated speed: ~227.6 tok/s
Bandwidth: 512 GB/s
12 GB VRAM
Estimated speed: ~224 tok/s
Bandwidth: 504 GB/s
12 GB VRAM
Estimated speed: ~224 tok/s
Bandwidth: 504 GB/s
12 GB VRAM
Estimated speed: ~224 tok/s
Bandwidth: 504 GB/s
8 GB VRAM
Estimated speed: ~220.4 tok/s
Bandwidth: 496 GB/s
11 GB VRAM
Estimated speed: ~215.1 tok/s
Bandwidth: 484 GB/s
12 GB VRAM
Estimated speed: ~202.7 tok/s
Bandwidth: 456 GB/s
8 GB VRAM
Estimated speed: ~199.1 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~199.1 tok/s
Bandwidth: 448 GB/s
16 GB VRAM
Estimated speed: ~199.1 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~199.1 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~199.1 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~199.1 tok/s
Bandwidth: 448 GB/s
8 GB VRAM
Estimated speed: ~199.1 tok/s
Bandwidth: 448 GB/s
12 GB VRAM
Estimated speed: ~192 tok/s
Bandwidth: 432 GB/s
12 GB VRAM
Estimated speed: ~192 tok/s
Bandwidth: 432 GB/s
12 GB VRAM
Estimated speed: ~192 tok/s
Bandwidth: 432 GB/s
64 GB VRAM
Estimated speed: ~177.8 tok/s
Bandwidth: 400 GB/s
96 GB VRAM
Estimated speed: ~177.8 tok/s
Bandwidth: 400 GB/s
128 GB VRAM
Estimated speed: ~177.8 tok/s
Bandwidth: 400 GB/s
8 GB VRAM
Estimated speed: ~170.7 tok/s
Bandwidth: 384 GB/s
12 GB VRAM
Estimated speed: ~170.7 tok/s
Bandwidth: 384 GB/s
12 GB VRAM
Estimated speed: ~160 tok/s
Bandwidth: 360 GB/s
6 GB VRAM
Estimated speed: ~149.3 tok/s
Bandwidth: 336 GB/s
6 GB VRAM
Estimated speed: ~149.3 tok/s
Bandwidth: 336 GB/s
6 GB VRAM
Estimated speed: ~149.3 tok/s
Bandwidth: 336 GB/s
8 GB VRAM
Estimated speed: ~142.2 tok/s
Bandwidth: 320 GB/s
16 GB VRAM
Estimated speed: ~128 tok/s
Bandwidth: 288 GB/s
8 GB VRAM
Estimated speed: ~128 tok/s
Bandwidth: 288 GB/s
6 GB VRAM
Estimated speed: ~128 tok/s
Bandwidth: 288 GB/s
16 GB VRAM
Estimated speed: ~128 tok/s
Bandwidth: 288 GB/s
8 GB VRAM
Estimated speed: ~128 tok/s
Bandwidth: 288 GB/s
8 GB VRAM
Estimated speed: ~128 tok/s
Bandwidth: 288 GB/s
8 GB VRAM
Estimated speed: ~124.4 tok/s
Bandwidth: 280 GB/s
48 GB VRAM
Estimated speed: ~121.3 tok/s
Bandwidth: 273 GB/s
8 GB VRAM
Estimated speed: ~120.9 tok/s
Bandwidth: 272 GB/s
8 GB VRAM
Estimated speed: ~113.8 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~113.8 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~113.8 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~113.8 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~113.8 tok/s
Bandwidth: 256 GB/s
8 GB VRAM
Estimated speed: ~99.6 tok/s
Bandwidth: 224 GB/s
8 GB VRAM
Estimated speed: ~99.6 tok/s
Bandwidth: 224 GB/s
32 GB VRAM
Estimated speed: ~88.9 tok/s
Bandwidth: 200 GB/s
32 GB VRAM
Estimated speed: ~88.9 tok/s
Bandwidth: 200 GB/s
32 GB VRAM
Estimated speed: ~88.9 tok/s
Bandwidth: 200 GB/s
6 GB VRAM
Estimated speed: ~85.3 tok/s
Bandwidth: 192 GB/s
6 GB VRAM
Estimated speed: ~85.3 tok/s
Bandwidth: 192 GB/s
4 GB VRAM
Estimated speed: ~85.3 tok/s
Bandwidth: 192 GB/s
6 GB VRAM
Estimated speed: ~85.3 tok/s
Bandwidth: 192 GB/s
36 GB VRAM
Estimated speed: ~66.7 tok/s
Bandwidth: 150 GB/s
4 GB VRAM
Estimated speed: ~56.9 tok/s
Bandwidth: 128 GB/s
32 GB VRAM
Estimated speed: ~53.3 tok/s
Bandwidth: 120 GB/s
4 GB VRAM
Estimated speed: ~49.8 tok/s
Bandwidth: 112 GB/s
24 GB VRAM
Estimated speed: ~44.4 tok/s
Bandwidth: 100 GB/s
24 GB VRAM
Estimated speed: ~44.4 tok/s
Bandwidth: 100 GB/s
16 GB VRAM
Estimated speed: ~30.2 tok/s
Bandwidth: 68 GB/s
3 GB VRAM
Estimated speed: ~59.7 tok/s
Bandwidth: 192 GB/s
| GPU | VRAM | Verdict | Estimated tok/s | Bandwidth | Where to Buy |
|---|---|---|---|---|---|
| NVIDIA GeForce RTX 5090 | 32 GB | Full GPU | ~796.4 | 1792 GB/s | |
| Apple M4 Ultra | 256 GB | Full GPU | ~485.3 | 1092 GB/s | |
| NVIDIA GeForce RTX 4090 | 24 GB | Full GPU | ~448 | 1008 GB/s | |
| NVIDIA GeForce RTX 3090 Ti | 24 GB | Full GPU | ~448 | 1008 GB/s | |
| NVIDIA GeForce RTX 5080 | 16 GB | Full GPU | ~426.7 | 960 GB/s | |
| AMD Radeon RX 7900 XTX | 24 GB | Full GPU | ~426.7 | 960 GB/s | |
| NVIDIA GeForce RTX 3090 | 24 GB | Full GPU | ~416 | 936 GB/s | |
| NVIDIA GeForce RTX 3080 Ti | 12 GB | Full GPU | ~405.3 | 912 GB/s | |
| NVIDIA GeForce RTX 3080 12GB | 12 GB | Full GPU | ~405.3 | 912 GB/s | |
| NVIDIA GeForce RTX 5070 Ti | 16 GB | Full GPU | ~398.2 | 896 GB/s | |
| AMD Radeon RX 7900 XT | 20 GB | Full GPU | ~355.6 | 800 GB/s | |
| Apple M1 Ultra | 128 GB | Full GPU | ~355.6 | 800 GB/s | |
| Apple M2 Ultra | 192 GB | Full GPU | ~355.6 | 800 GB/s | |
| Apple M3 Ultra | 192 GB | Full GPU | ~355.6 | 800 GB/s | |
| NVIDIA GeForce RTX 3080 10GB | 10 GB | Full GPU | ~337.8 | 760 GB/s | |
| NVIDIA GeForce RTX 4080 Super | 16 GB | Full GPU | ~327.1 | 736 GB/s | |
| NVIDIA GeForce RTX 4080 | 16 GB | Full GPU | ~318.7 | 717 GB/s | |
| NVIDIA GeForce RTX 5070 | 12 GB | Full GPU | ~298.7 | 672 GB/s | |
| NVIDIA GeForce RTX 4070 Ti Super | 16 GB | Full GPU | ~298.7 | 672 GB/s | |
| AMD Radeon RX 7800 XT | 16 GB | Full GPU | ~277.3 | 624 GB/s | |
| NVIDIA GeForce RTX 2080 Ti | 11 GB | Full GPU | ~273.8 | 616 GB/s | |
| NVIDIA GeForce RTX 3070 Ti | 8 GB | Full GPU | ~270.2 | 608 GB/s | |
| NVIDIA GeForce RTX 4090 Laptop | 16 GB | Full GPU | ~256 | 576 GB/s | |
| AMD Radeon RX 7900 GRE | 16 GB | Full GPU | ~256 | 576 GB/s | |
| AMD Radeon RX 6950 XT | 16 GB | Full GPU | ~256 | 576 GB/s | |
| Intel Arc A770 16GB | 16 GB | Full GPU | ~248.9 | 560 GB/s | |
| Apple M4 Max | 128 GB | Full GPU | ~242.7 | 546 GB/s | |
| AMD Radeon RX 6900 XT | 16 GB | Full GPU | ~227.6 | 512 GB/s | |
| AMD Radeon RX 6800 XT | 16 GB | Full GPU | ~227.6 | 512 GB/s | |
| AMD Radeon RX 6800 | 16 GB | Full GPU | ~227.6 | 512 GB/s | |
| Intel Arc A770 8GB | 8 GB | Full GPU | ~227.6 | 512 GB/s | |
| Intel Arc A750 | 8 GB | Full GPU | ~227.6 | 512 GB/s | |
| Intel Arc A580 | 8 GB | Full GPU | ~227.6 | 512 GB/s | |
| NVIDIA GeForce RTX 4070 Ti | 12 GB | Full GPU | ~224 | 504 GB/s | |
| NVIDIA GeForce RTX 4070 Super | 12 GB | Full GPU | ~224 | 504 GB/s | |
| NVIDIA GeForce RTX 4070 | 12 GB | Full GPU | ~224 | 504 GB/s | |
| NVIDIA GeForce RTX 2080 Super | 8 GB | Full GPU | ~220.4 | 496 GB/s | |
| NVIDIA GeForce GTX 1080 Ti | 11 GB | Full GPU | ~215.1 | 484 GB/s | |
| Intel Arc B580 | 12 GB | Full GPU | ~202.7 | 456 GB/s | |
| NVIDIA GeForce RTX 3070 | 8 GB | Full GPU | ~199.1 | 448 GB/s | |
| NVIDIA GeForce RTX 3060 Ti | 8 GB | Full GPU | ~199.1 | 448 GB/s | |
| NVIDIA GeForce RTX 3080 Laptop | 16 GB | Full GPU | ~199.1 | 448 GB/s | |
| NVIDIA GeForce RTX 2080 | 8 GB | Full GPU | ~199.1 | 448 GB/s | |
| NVIDIA GeForce RTX 2070 Super | 8 GB | Full GPU | ~199.1 | 448 GB/s | |
| NVIDIA GeForce RTX 2070 | 8 GB | Full GPU | ~199.1 | 448 GB/s | |
| NVIDIA GeForce RTX 2060 Super | 8 GB | Full GPU | ~199.1 | 448 GB/s | |
| NVIDIA GeForce RTX 4080 Laptop | 12 GB | Full GPU | ~192 | 432 GB/s | |
| AMD Radeon RX 7700 XT | 12 GB | Full GPU | ~192 | 432 GB/s | |
| AMD Radeon RX 6750 XT | 12 GB | Full GPU | ~192 | 432 GB/s | |
| Apple M1 Max | 64 GB | Full GPU | ~177.8 | 400 GB/s | |
| Apple M2 Max | 96 GB | Full GPU | ~177.8 | 400 GB/s | |
| Apple M3 Max | 128 GB | Full GPU | ~177.8 | 400 GB/s | |
| NVIDIA GeForce RTX 3070 Laptop | 8 GB | Full GPU | ~170.7 | 384 GB/s | |
| AMD Radeon RX 6700 XT | 12 GB | Full GPU | ~170.7 | 384 GB/s | |
| NVIDIA GeForce RTX 3060 | 12 GB | Full GPU | ~160 | 360 GB/s | |
| NVIDIA GeForce RTX 3060 Laptop | 6 GB | Full GPU | ~149.3 | 336 GB/s | |
| NVIDIA GeForce RTX 2060 | 6 GB | Full GPU | ~149.3 | 336 GB/s | |
| NVIDIA GeForce GTX 1660 Super | 6 GB | Full GPU | ~149.3 | 336 GB/s | |
| NVIDIA GeForce GTX 1080 | 8 GB | Full GPU | ~142.2 | 320 GB/s | |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16 GB | Full GPU | ~128 | 288 GB/s | |
| NVIDIA GeForce RTX 4060 Ti 8GB | 8 GB | Full GPU | ~128 | 288 GB/s | |
| NVIDIA GeForce GTX 1660 Ti | 6 GB | Full GPU | ~128 | 288 GB/s | |
| AMD Radeon RX 7600 XT | 16 GB | Full GPU | ~128 | 288 GB/s | |
| AMD Radeon RX 7600 | 8 GB | Full GPU | ~128 | 288 GB/s | |
| AMD Radeon RX 7600M XT | 8 GB | Full GPU | ~128 | 288 GB/s | |
| AMD Radeon RX 6650 XT | 8 GB | Full GPU | ~124.4 | 280 GB/s | |
| Apple M4 Pro | 48 GB | Full GPU | ~121.3 | 273 GB/s | |
| NVIDIA GeForce RTX 4060 | 8 GB | Full GPU | ~120.9 | 272 GB/s | |
| NVIDIA GeForce RTX 4070 Laptop | 8 GB | Full GPU | ~113.8 | 256 GB/s | |
| NVIDIA GeForce RTX 4060 Laptop | 8 GB | Full GPU | ~113.8 | 256 GB/s | |
| NVIDIA GeForce GTX 1070 Ti | 8 GB | Full GPU | ~113.8 | 256 GB/s | |
| NVIDIA GeForce GTX 1070 | 8 GB | Full GPU | ~113.8 | 256 GB/s | |
| AMD Radeon RX 6600 XT | 8 GB | Full GPU | ~113.8 | 256 GB/s | |
| NVIDIA GeForce RTX 3050 | 8 GB | Full GPU | ~99.6 | 224 GB/s | |
| AMD Radeon RX 6600 | 8 GB | Full GPU | ~99.6 | 224 GB/s | |
| Apple M1 Pro (10-core GPU) | 32 GB | Full GPU | ~88.9 | 200 GB/s | |
| Apple M1 Pro (16-core GPU) | 32 GB | Full GPU | ~88.9 | 200 GB/s | |
| Apple M2 Pro | 32 GB | Full GPU | ~88.9 | 200 GB/s | |
| NVIDIA GeForce RTX 4050 Laptop | 6 GB | Full GPU | ~85.3 | 192 GB/s | |
| NVIDIA GeForce GTX 1660 | 6 GB | Full GPU | ~85.3 | 192 GB/s | |
| NVIDIA GeForce GTX 1650 Super | 4 GB | Full GPU | ~85.3 | 192 GB/s | |
| NVIDIA GeForce GTX 1060 6GB | 6 GB | Full GPU | ~85.3 | 192 GB/s | |
| Apple M3 Pro | 36 GB | Full GPU | ~66.7 | 150 GB/s | |
| NVIDIA GeForce GTX 1650 | 4 GB | Full GPU | ~56.9 | 128 GB/s | |
| Apple M4 | 32 GB | Full GPU | ~53.3 | 120 GB/s | |
| NVIDIA GeForce GTX 1050 Ti | 4 GB | Full GPU | ~49.8 | 112 GB/s | |
| Apple M2 | 24 GB | Full GPU | ~44.4 | 100 GB/s | |
| Apple M3 | 24 GB | Full GPU | ~44.4 | 100 GB/s | |
| Apple M1 | 16 GB | Full GPU | ~30.2 | 68 GB/s | |
| NVIDIA GeForce GTX 1060 3GB | 3 GB | Partial GPU | ~59.7 | 192 GB/s |