GPU comparison
NVIDIA RTX 4090 (24GB) vs NVIDIA RTX 5070 (12GB) 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 4090 (24GB) | NVIDIA RTX 5070 (12GB) | |
|---|---|---|
| Memory | 24.0 GB | 12.0 GB |
| Bandwidth | 1008 GB/s | 672 GB/s |
| Price (approx) | $2,999 | $629 |
| LLMs it runs | 34 of 48 | 19 of 48 |
| Best model it runs | Gemma 4 31B · 41–62 tok/s | Devstral Small 2 24B · 45–68 tok/s |
The NVIDIA RTX 4090 (24GB) runs 15 more of the tracked models (34 vs 19), 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.