can-i-run-this-llm

GPU comparison

NVIDIA RTX 3090 (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 34 tracked models each one can run.

NVIDIA RTX 3090 (24GB)NVIDIA RTX 5070 (12GB)
Memory24.0 GB12.0 GB
Bandwidth936 GB/s672 GB/s
Price (approx)$1,099$629
LLMs it runs25 of 3413 of 34
Best model it runsGemma 4 31B · 39–58 tok/sDevstral Small 2 24B · 45–68 tok/s

The NVIDIA RTX 3090 (24GB) runs 12 more of the tracked models (25 vs 13), thanks to its 24.0 GB of memory. The NVIDIA RTX 3090 (24GB) has more memory bandwidth (936 GB/s), so it generates tokens faster at the same model and quant.

What the NVIDIA RTX 3090 (24GB) runs →What the NVIDIA RTX 5070 (12GB) runs →Open the calculator →