GPU comparison
NVIDIA RTX 3060 (12GB) vs NVIDIA RTX 6000 Ada (48GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 48 tracked models each one can run.
| NVIDIA RTX 3060 (12GB) | NVIDIA RTX 6000 Ada (48GB) | |
|---|---|---|
| Memory | 12.0 GB | 48.0 GB |
| Bandwidth | 360 GB/s | 960 GB/s |
| Price (approx) | $329 | $6,800 |
| LLMs it runs | 19 of 48 | 37 of 48 |
| Best model it runs | Devstral Small 2 24B · 26–39 tok/s | Gemma 4 31B · 20–30 tok/s |
The NVIDIA RTX 6000 Ada (48GB) runs 18 more of the tracked models (37 vs 19), thanks to its 48.0 GB of memory. The NVIDIA RTX 6000 Ada (48GB) has more memory bandwidth (960 GB/s), so it generates tokens faster at the same model and quant.