can-i-run-this-llm

GPU comparison

NVIDIA DGX Spark (GB10, 128GB) 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 DGX Spark (GB10, 128GB)NVIDIA RTX 5070 (12GB)
Memory128.0 GB12.0 GB
Bandwidth273 GB/s672 GB/s
Price (approx)$4,699$629
LLMs it runs30 of 3413 of 34
Best model it runsGemma 4 31B · 11–16 tok/sDevstral Small 2 24B · 45–68 tok/s

The NVIDIA DGX Spark (GB10, 128GB) runs 17 more of the tracked models (30 vs 13), thanks to its 128.0 GB of memory. The NVIDIA RTX 5070 (12GB) has more memory bandwidth (672 GB/s), so it generates tokens faster at the same model and quant.

What the NVIDIA DGX Spark (GB10, 128GB) runs →What the NVIDIA RTX 5070 (12GB) runs →Open the calculator →