

NVIDIA A10G wins 7 of 11 benchmarks, averaging 70.8% 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 A10G leads by 190% (2.2 vs 6.38 images/min); the closest fight is Qwen3 4B (10% apart); VRAM decides part of this one: NVIDIA GeForce RTX 3060 Ti runs 137 of our 12 AI workloads while the other card runs 3, models that don't fit score zero.
| Benchmark | NVIDIA GeForce RTX 3060 Ti | NVIDIA A10G | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 118.21 | 129.87 | -9% |
| Llama 3.1 8B tok/s | 76.93 | 86.62 | -11% |
| Qwen2.5-Coder 14B tok/s | 0 | 47.07 | n/a |
| Qwen3 32B tok/s | 0 | 22.04 | n/a |
| Llama 3.3 70B tok/s | 0 | 0 | n/a |
| Stable Diffusion XL images/min | 2.2 | 6.38 | -66% |
| Z-Image Turbo images/min | 0 | 3.45 | n/a |
| FLUX.1 dev images/min | 0 | 0 | n/a |
| FLUX.1 Kontext dev images/min | 0 | 0 | n/a |
| Qwen-Image-Edit images/min | 0 | 0 | n/a |
| Wan 2.2 5B (720p) frames/s | 0 | 0.18 | n/a |
| NVIDIA GeForce RTX 3060 Ti | NVIDIA A10G | |
|---|---|---|
| VRAM | 8GB | 24GB |
| Architecture | Ampere (GA104) | Ampere |
| Memory bandwidth | 448 GB/s | 600 GB/s |
| Boost clock | 1,665 MHz | 1,710 MHz |
| TDP | 200 W | 150 W |
| Launch MSRP | $399 | $2,800 |
| Release | 2020-12-02 | 2021-11-01 |
NVIDIA GeForce RTX 3060 Ti full review · NVIDIA A10G full review · All AI & Machine Learning rankings