§01·compatibility · /check
Z-Image Turbo on RTX 3090
Yes — Z-Image Turbo runs on the RTX 3090 (24 GB). Fastest community-measured result: 9 s.
✓ runsimageactive30 series24GB VRAM
step-by-step recipe for this pair
Z-Image Turbo on RTX 3090: 8-Step 1024x1024 Text-to-Image at BF16 with Diffusers or ComfyUI
imagebeginner16GB+
§02·benchmarks
| Task | Quant | Speed | VRAM | Works | Confidence | Source | Verified |
|---|---|---|---|---|---|---|---|
| t2i | bf16 | 9s | ✓ | miroleon.github.io· community-benchmark-sibling | 2026-05-27 |
§03·how it was measured
- t2ibf169 s
Sibling-cited from miroleon RTX 3090 Ti benchmark project (6.74s end-to-end @ 7-step BF16, 0.89 s/it). Scaled to ~9s at 8-NFE for the slightly-slower non-Ti 3090 (Ampere sm_86, ~10% lower FP16 compute, ~7-10% lower bandwidth than 3090 Ti). VRAM peak inherited 13GB — arch-invariant for the same BF16 weight set.
recorded from miroleon.github.io ↗ · verified 2026-05-27
§04·more Z-Image Turbo recipes
- imagebeginner6GB+
Z-Image Turbo on Apple M2 Pro: 8-step 1024x1024 text-to-image in 16 GB unified memory with mflux
- imagebeginner17GB+
Z-Image Turbo on Apple M3 Max: 8-step 1024x1024 text-to-image in unified memory with mflux
- imagebeginner17GB+
Z-Image Turbo on Apple M4 Max: 8-step 1024x1024 text-to-image in unified memory with mflux
- imagebeginner17GB+
Z-Image Turbo on Apple M2 Max: 8-step 1024x1024 text-to-image in unified memory with mflux
§05·common questions
Can you run Z-Image Turbo on RTX 3090?
Yes — Z-Image Turbo runs on the RTX 3090 (24 GB). Fastest community-measured result: 9 s.
Which quantizations have been tested for Z-Image Turbo on RTX 3090?
bf16 — measured in community benchmarks.
How fast is Z-Image Turbo on RTX 3090?
9 s (t2i) in the fastest community-measured run.
Are there step-by-step instructions for Z-Image Turbo on RTX 3090?
Yes — a step-by-step recipe documents Z-Image Turbo on the RTX 3090, linked at the top of this page.