

NVIDIA RTX 6000 Ada Generation wins 9 of 9 benchmarks, averaging 221.9% faster.
Both cards were measured first-party on our bench, same suite, same test rig.
The gap is widest in Stable Diffusion XL, where NVIDIA RTX 6000 Ada Generation leads by 285% (2.78 vs 10.7 images/min); the closest fight is Qwen3 4B (179% apart); VRAM decides part of this one: NVIDIA RTX 6000 Ada Generation runs 9 of our 12 AI workloads while the other card runs 3, models that don't fit score zero.
| Benchmark | GeForce RTX 4060 | NVIDIA RTX 6000 Ada Generation | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 86.38 | 241.33 | -64% |
| Llama 3.1 8B tok/s | 52.4 | 157.89 | -67% |
| Qwen2.5-Coder 14B tok/s | 0 | 87.51 | n/a |
| Qwen3 32B tok/s | 0 | 39.87 | n/a |
| Llama 3.3 70B tok/s | 0 | 18.4 | n/a |
| Stable Diffusion XL images/min | 2.78 | 10.7 | -74% |
| Z-Image Turbo images/min | 0 | 5.1 | n/a |
| FLUX.1 dev images/min | 0 | 2.229 | n/a |
| FLUX.1 Kontext dev images/min | 0 | 1.029 | n/a |
| GeForce RTX 4060 | NVIDIA RTX 6000 Ada Generation | |
|---|---|---|
| VRAM | 8GB | 48GB |
| Architecture | Ada Lovelace | Ada Lovelace |
| Memory bandwidth | 272 GB/s | 960 GB/s |
| Boost clock | 2,475 MHz | 2,505 MHz |
| TDP | 115 W | 300 W |
| Launch MSRP | $299 | $6,799 |
| Release | 2023-05-24 | 2022-12-03 |
GeForce RTX 4060 full review · NVIDIA RTX 6000 Ada Generation full review · All AI & Machine Learning rankings