GPU comparison
NVIDIA RTX 4090 (24GB) vs NVIDIA RTX 5060 Ti (16GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 34 tracked models each one can run.
| NVIDIA RTX 4090 (24GB) | NVIDIA RTX 5060 Ti (16GB) | |
|---|---|---|
| Memory | 24.0 GB | 16.0 GB |
| Bandwidth | 1008 GB/s | 448 GB/s |
| Price (approx) | $2,999 | $549 |
| LLMs it runs | 25 of 34 | 18 of 34 |
| Best model it runs | Gemma 4 31B · 41–62 tok/s | Gemma 4 26B-A4B (MoE) · 103–155 tok/s |
The NVIDIA RTX 4090 (24GB) runs 7 more of the tracked models (25 vs 18), thanks to its 24.0 GB of memory. The NVIDIA RTX 4090 (24GB) has more memory bandwidth (1008 GB/s), so it generates tokens faster at the same model and quant.