§01·compatibility · /check
Krea 2 on RTX 3090
Yes — Krea 2 runs on the RTX 3090 (24 GB). Fastest community-measured result: 14.75 s/img, with 18.75 GB peak VRAM.
✓ runsimageactive30 series24GB VRAM
§02·benchmarks
| Task | Quant | Speed | VRAM | Works | Confidence | Source | Verified |
|---|---|---|---|---|---|---|---|
| text-to-image | fp8 | 14.75s/img | 18.75GB | ✓ | github.com· github | 2026-06-24 |
§03·common questions
Can you run Krea 2 on RTX 3090?
Yes — Krea 2 runs on the RTX 3090 (24 GB). Fastest community-measured result: 14.75 s/img, with 18.75 GB peak VRAM.
How much VRAM does Krea 2 need on RTX 3090?
Measured peak VRAM is 18.75 GB — about 5.3 GB of headroom on the 24 GB card.
Which quantizations have been tested for Krea 2 on RTX 3090?
fp8 — measured in community benchmarks.
How fast is Krea 2 on RTX 3090?
Up to 14.75 s/img (text-to-image), the fastest community-measured result.
Are there step-by-step instructions for Krea 2 on RTX 3090?
Yes — a step-by-step recipe documents Krea 2 on the RTX 3090; see the recipes listed below.
§04·related recipes
- imageintermediate16GB+
Krea 2 Turbo (FP8) on RTX 3090 via ComfyUI: 8-Step Text-to-Image, with the Raw Tier in Reach
- imageintermediate24GB+
Krea 2 Turbo on Apple M3 Max: 8-Step Text-to-Image in Unified Memory via ComfyUI (MPS)
- imageintermediate24GB+
Krea 2 Turbo on Apple M4 Max: 8-Step Text-to-Image in Unified Memory via ComfyUI (MPS)
- imageintermediate24GB+
Krea 2 Turbo on Apple M2 Max: 8-Step Text-to-Image in Unified Memory via ComfyUI (MPS)
- imageintermediate16GB+
Krea 2 Turbo on RX 7800 XT via ComfyUI + ROCm: GGUF Text-to-Image in 16GB