

NVIDIA L4 wins 5 of 11 benchmarks, averaging -19.5% faster.
Both cards were measured first-party on our bench, same suite, same test rig.
The gap is widest in Llama 3.1 8B, where NVIDIA GeForce RTX 3070 Ti leads by 102% (102.13 vs 50.45 tok/s); the closest fight is Stable Diffusion XL (38% apart); VRAM decides part of this one: NVIDIA GeForce RTX 3070 Ti runs 138 of our 12 AI workloads while the other card runs 3, models that don't fit score zero.
| Benchmark | NVIDIA GeForce RTX 3070 Ti | NVIDIA L4 | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 154.65 | 84 | +84% |
| Llama 3.1 8B tok/s | 102.13 | 50.45 | +102% |
| Qwen2.5-Coder 14B tok/s | 0 | 27.46 | n/a |
| Qwen3 32B tok/s | 0 | 12.42 | n/a |
| Llama 3.3 70B tok/s | 0 | 0 | n/a |
| Stable Diffusion XL images/min | 3.76 | 5.18 | -27% |
| Z-Image Turbo images/min | 0 | 2.475 | 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 | 0.15 | n/a |
| NVIDIA GeForce RTX 3070 Ti | NVIDIA L4 | |
|---|---|---|
| VRAM | 8GB | 24GB |
| Architecture | Ampere (GA104) | Ada Lovelace |
| Memory bandwidth | 608 GB/s | 300 GB/s |
| Boost clock | 1,770 MHz | 2,040 MHz |
| TDP | 290 W | 72 W |
| Launch MSRP | $599 | $2,500 |
| Release | 2021-06-10 | 2023-03-21 |
NVIDIA GeForce RTX 3070 Ti full review · NVIDIA L4 full review · All AI & Machine Learning rankings