From the RTX 3090 24 GB to the RTX 4090 24 GB: what changes for local AI
For what fits in memory, nothing changes: all 50 models get the same file on both cards. Any gain is speed alone. Note that the RTX 4090 24 GB has the same amount of VRAM.
0newly run well
0better file
50no change
+0GB more VRAM
01No change in what fits
FLUX.1 dev Runs wellFLUX.1 schnell Runs wellFLUX.1 Kontext Runs wellFLUX.1 Krea Runs wellFLUX.1 Fill Runs wellFLUX.2 dev RunsFLUX.2 klein 9B Runs wellFLUX.2 klein 4B Runs wellKrea 2 Runs wellQwen-Image Runs wellQwen-Image-Edit Runs wellQwen-Image 2.1 Runs wellZ-Image Turbo Runs wellZ-Image Runs wellIdeogram 4 Runs wellBoogu-Image Runs wellERNIE-Image Runs wellHiDream-O1 Runs wellMage-Flow Runs wellMing-Image Runs wellLumina 2.0 Runs wellHiDream-I1 Full Runs wellHiDream-I1 Runs wellSD 3.5 Large Runs wellSD 3.5 Medium Runs wellChroma1-HD Runs wellSDXL Runs wellIllustrious / Pony Runs wellSD 1.5 Runs wellHunyuanImage 2.1 Runs wellWan 2.1 14B Runs wellWan 2.1 1.3B Runs wellWan 2.1 I2V 480P Runs wellWan 2.1 I2V 720P Runs wellWan VACE 14B Runs wellWan 2.2 T2V Runs wellWan 2.2 I2V Runs wellWan 2.2 5B Runs wellWan 2.2 Animate Runs wellWan Animate 2 Runs wellWan 2.2 S2V Runs wellSCAIL-2 Runs wellHunyuanVideo 13B Runs wellLTX-Video 13B Runs wellHunyuanVideo 1.5 Runs wellLTX-2 RunsLTX-2.3 RunsLTX-2.5 RunsMiniMax H3 TightMiniMax H3 Pruned Runs
Same verdict and same file on both cards. Speed can still differ.
02Speed and features
Memory bandwidth goes from 936 to 1008 GB/s (×1.08). A rough guide to speed, 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.