Home › GPUs & Macs › NVIDIA RTX 2070 vs NVIDIA RTX 5060 Ti
NVIDIA RTX 2070 vs NVIDIA RTX 5060 Ti for local LLMs
Across 2 tests measured on both, the two are about even (median ratio 1.03×).
On Llama 3.1 8B Instruct (Q4_K_M, LocalScore) the NVIDIA RTX 2070 generates 52.4 tokens/s and the NVIDIA RTX 5060 Ti 55.1 tokens/s (measured).
Same model, same quant, same test
| Model | Quant / test | RTX 2070 tok/s | RTX 5060 Ti tok/s | Faster | Sources and run details |
|---|---|---|---|---|---|
| Llama 3.1 8B Instruct | Q4_K_M LocalScore | 52.4 llamafile | 55.1 llamafile | RTX 5060 Ti +5% | LocalScore RTX 2070 · LocalScore RTX 5060 Ti |
| Llama 3.2 1B Instruct | Q4_K_M LocalScore | 190 llamafile | 170 llamafile | RTX 2070 +12% | LocalScore RTX 2070 · LocalScore RTX 5060 Ti |
Generation speed in tokens/s, best measured backend for each chip (shown under the number). Backends can differ between the two chips; check them before drawing conclusions. Measured results only, nothing estimated.
Specs
| NVIDIA RTX 2070 | NVIDIA RTX 5060 Ti | |
|---|---|---|
| Memory | 8 GB | 16 GB |
| Memory bandwidth | 448 GB/s | 448 GB/s |
All results for the NVIDIA RTX 2070 · All results for the NVIDIA RTX 5060 Ti · More comparisons