Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

From the RTX 3090 24 GB to the RTX 4090 24 GB: what changes for local AI

+0 GB of VRAM (24 → 24 GB). Of 49 models, 0 newly run well, 0 get a better file or stop offloading, and 49 stay the same.

24 GB GDDR6X · 384-bit · 936 GB/s · Ampere24 GB GDDR6X · 384-bit · 1008 GB/s · Ada LovelaceData 2026-09-25
0newly run well
0better file
49no change
+0GB more VRAM

02Speed and features

Memory bandwidth goes from 936 to 1008 GB/s (×1.08). For models that fit on both cards, bandwidth and compute decide the speed; this ratio is a rough first guide, not a benchmark. The RTX 4090 24 GB computes FP8 natively, so FP8 files run faster there than on the RTX 3090 24 GB, which only uses them to save memory.