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 5090 32 GB: what changes for local AI

+8 GB of VRAM (24 → 32 GB). Of 49 models, 4 newly run well, 9 get a better file or stop offloading, and 36 stay the same.

24 GB GDDR6X · 384-bit · 936 GB/s · Ampere32 GB GDDR7 · 512-bit · 1792 GB/s · BlackwellData 2026-09-25
4newly run well
9better file
36no change
+8GB more VRAM

01Newly runs well

ModelOn the RTX 3090 24 GBOn the RTX 5090 32 GBNeeded
LTX-2 (19B)Runs Q6_KRuns well Q8_025.2 GB
LTX-2.3 (22B)Runs Q6_KRuns well Q8_027.6 GB
LTX-2.5 (22B)Runs Q6_KRuns well Q8_028.4 GB
MiniMax H3 PrunedRuns Q6_KRuns well FP826.8 GB

“Runs well” means a 16-bit or 8-bit file fits entirely in VRAM.

02A better file, or less offloading

ModelOn the RTX 3090 24 GBOn the RTX 5090 32 GBNeeded
FLUX.1 [dev]Runs well Q8_0Runs well 16-bit26.1 GB
FLUX.1 [schnell]Runs well Q8_0Runs well 16-bit26.1 GB
FLUX.1 Kontext [dev]Runs well Q8_0Runs well 16-bit26.4 GB
FLUX.1 Krea [dev]Runs well Q8_0Runs well 16-bit26.1 GB
FLUX.1 Fill [dev]Runs well Q8_0Runs well 16-bit26.4 GB
FLUX.2 [dev]Runs Q4_K_MRuns Q6_K30.7 GB
Krea 2 (Turbo)Runs well Q8_0Runs well 16-bit28.9 GB
HunyuanVideo (13B, original)Runs well Q8_0Runs well 16-bit29.9 GB
MiniMax H3 (33B)Tight Q3_K_MRuns Q5_K_M29.7 GB

04Speed and features

Memory bandwidth goes from 936 to 1792 GB/s (×1.91). 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 5090 32 GB computes FP8 natively, so FP8 files run faster there than on the RTX 3090 24 GB, which only uses them to save memory. It also adds FP4 (NVFP4) hardware, for models that ship NVFP4 files.