Home › GPUs & Macs › NVIDIA RTX 2060 SUPER vs NVIDIA RTX 5060 Ti
NVIDIA RTX 2060 SUPER vs NVIDIA RTX 5060 Ti for local LLMs
Across 3 tests measured on both, the NVIDIA RTX 5060 Ti is faster in 2 and generates a median 1.10× the tokens/s of the NVIDIA RTX 2060 SUPER.
On Llama 2 7B (Q4_0, llama-bench) the NVIDIA RTX 2060 SUPER generates 61.1 tokens/s and the NVIDIA RTX 5060 Ti 97.0 tokens/s (measured).
Same model, same quant, same test
| Model | Quant / test | RTX 2060 SUPER tok/s | RTX 5060 Ti tok/s | Faster | Sources and run details |
|---|---|---|---|---|---|
| Llama 2 7B | Q4_0 llama-bench | 61.1 CUDA | 97.0 Vulkan | RTX 5060 Ti +59% | llama.cpp #15013 RTX 2060 SUPER · llama.cpp #10879 RTX 5060 Ti |
| Llama 3.1 8B Instruct | Q4_K_M LocalScore | 49.9 llamafile | 55.1 llamafile | RTX 5060 Ti +10% | LocalScore RTX 2060 SUPER · LocalScore RTX 5060 Ti |
| Llama 3.2 1B Instruct | Q4_K_M LocalScore | 199 llamafile | 170 llamafile | RTX 2060 SUPER +17% | LocalScore RTX 2060 SUPER · 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 2060 SUPER | NVIDIA RTX 5060 Ti | |
|---|---|---|
| Memory | 8 GB | 16 GB |
| Memory bandwidth | 448 GB/s | 448 GB/s |
All results for the NVIDIA RTX 2060 SUPER · All results for the NVIDIA RTX 5060 Ti · More comparisons