GPU comparison
NVIDIA RTX 4070 (12GB) vs AMD RX 9070 (16GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 64 tracked models each one can run.
| NVIDIA RTX 4070 (12GB) | AMD RX 9070 (16GB) | |
|---|---|---|
| Memory | 12.0 GB | 16.0 GB |
| Bandwidth | 504 GB/s | 645 GB/s |
| Price (approx) | $549 | $569 |
| LLMs it runs | 27 of 64 | 45 of 64 |
| Best model it runs | Devstral Small 2 24B · 35–53 tok/s | Qwen3.8 27B · 38–58 tok/s |
The AMD RX 9070 (16GB) runs 18 more of the tracked models (45 vs 27), thanks to its 16.0 GB of memory. The AMD RX 9070 (16GB) has more memory bandwidth (645 GB/s), so it generates tokens faster at the same model and quant.