GPU comparison
NVIDIA RTX 5080 (16GB) vs Intel Arc B580 (12GB) 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 5080 (16GB) | Intel Arc B580 (12GB) | |
|---|---|---|
| Memory | 16.0 GB | 12.0 GB |
| Bandwidth | 960 GB/s | 456 GB/s |
| Price (approx) | $1,399 | $289 |
| LLMs it runs | 18 of 34 | 13 of 34 |
| Best model it runs | Gemma 4 26B-A4B (MoE) · 167–251 tok/s | Devstral Small 2 24B · 32–48 tok/s |
The NVIDIA RTX 5080 (16GB) runs 5 more of the tracked models (18 vs 13), thanks to its 16.0 GB of memory. The NVIDIA RTX 5080 (16GB) has more memory bandwidth (960 GB/s), so it generates tokens faster at the same model and quant.