Hardware comparison
NVIDIA RTX 5060 (8GB) vs NVIDIA RTX 5080 (16GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 69 tracked models each one can run.
Scroll sideways to compare both machines. Keyboard: focus the table, then use the arrow keys. Metric names stay visible.
| Hardware | NVIDIA RTX 5060 (8GB) | NVIDIA RTX 5080 (16GB) |
|---|---|---|
| Memory | 8.0 GB | 16.0 GB (better for this comparison) |
| Bandwidth | 448 GB/s | 960 GB/s (better for this comparison) |
| Price (approx) | $449 (better for this comparison)GPU only · host PC required, sold separately | $1,399GPU only · host PC required, sold separately |
| LLMs it runs | 23 of 69 | 48 of 69 (better for this comparison) |
| Best model it runs | Gemma 3 12BQ2_K · estimated 53–79 tok/s | Gemma 4 31BQ2_K · estimated 48–71 tok/s |
Both prices cover GPU cards only. A host PC is required and its cost is excluded. Prices are approximate catalog estimates; check current configurations and prices before buying.
The recommended models differ. These estimated speeds are not a like-for-like comparison. Estimates use 4,096 context tokens, llama.cpp and one stream.
The NVIDIA RTX 5080 (16GB) runs 25 more of the tracked models (48 vs 23), thanks to its 16.0 GB of memory. The NVIDIA RTX 5080 (16GB) has more memory bandwidth (960 GB/s). Higher bandwidth can help generation speed, but model, quant, architecture and runtime also affect the estimates.