Home › GPUs & Macs › NVIDIA RTX 5060 Ti vs NVIDIA RTX 4060 Ti
NVIDIA RTX 5060 Ti vs NVIDIA RTX 4060 Ti for local LLMs
Across 4 tests measured on both, the NVIDIA RTX 5060 Ti is faster in 4 and generates a median 1.39× the tokens/s of the NVIDIA RTX 4060 Ti.
On Llama 2 7B (Q4_0, llama-bench) the NVIDIA RTX 5060 Ti generates 97.0 tokens/s and the NVIDIA RTX 4060 Ti 64.0 tokens/s (measured).
Same model, same quant, same test
| Model | Quant / test | RTX 5060 Ti tok/s | RTX 4060 Ti tok/s | Faster | Sources and run details |
|---|---|---|---|---|---|
| Llama 2 7B | Q4_0 llama-bench | 97.0 Vulkan | 64.0 CUDA | RTX 5060 Ti +52% | llama.cpp #10879 RTX 5060 Ti · llama.cpp #15013 RTX 4060 Ti |
| Llama 3.1 8B Instruct | Q4_K_M LocalScore | 55.1 llamafile | 43.3 llamafile | RTX 5060 Ti +27% | LocalScore RTX 5060 Ti · LocalScore RTX 4060 Ti |
| Llama 3.2 1B Instruct | Q4_K_M LocalScore | 170 llamafile | 167 llamafile | even | LocalScore RTX 5060 Ti · LocalScore RTX 4060 Ti |
| Qwen2.5 14B Instruct | Q4_K_M LocalScore | 27.7 llamafile | 14.6 llamafile | RTX 5060 Ti +91% | LocalScore RTX 5060 Ti · LocalScore RTX 4060 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 5060 Ti | NVIDIA RTX 4060 Ti | |
|---|---|---|
| Memory | 16 GB | 8 GB |
| Memory bandwidth | 448 GB/s | 288 GB/s |
All results for the NVIDIA RTX 5060 Ti · All results for the NVIDIA RTX 4060 Ti · More comparisons