Can the RTX 5090 32 GB run Krea 2 (Turbo)?
Yes. 16-bit fits on the RTX 5090 32 GB with 3.1 GB to spare.
Take 16-bit (26.3 GB). In use it comes to about 28.9 GB, with 3.1 GB left over on 32 GB.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | krea2_turbo_bf16.safetensors 16-bit · Comfy-Org/Krea-2 | models/diffusion_models | 26.3 GB | Download → |
| Text encoder | qwen3vl_4b_fp8_scaled.safetensors Qwen3-VL 4B FP8 · Comfy-Org/Krea-2 | models/text_encoders | 5.2 GB | Download → |
| VAE | qwen_image_vae.safetensors Qwen-Image VAE · Comfy-Org/Krea-2 | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 31.8 GB | |||
Alternatives: Qwen3-VL 4B BF16 (8.9 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: INT8 workflow (.json). Drag the file into ComfyUI. All workflows →
System RAM: 48 GB or more. These files take about 31.8 GB of RAM while loaded, 37.8 GB with Windows and ComfyUI. What happens with less. calculated
02Every Krea 2 file on 32 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · Comfy-Org | 26.3 GB | 28.9 GB | fits · 3.1 GB spare | the original weights | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 13.1 GB | 15.7 GB | fits · 16.3 GB spare | practically identical to the original | Hugging Face → |
| INT8 SAFETENSORS · Comfy-Org | 13.5 GB | 16.1 GB | fits · 15.9 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · vantagewithai | 13.7 GB | 16.3 GB | fits · 15.7 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · vantagewithai | 10.6 GB | 13.2 GB | fits · 18.8 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · vantagewithai | 8.9 GB | 11.5 GB | fits · 20.5 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · vantagewithai | 7.5 GB | 10.1 GB | fits · 21.9 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · vantagewithai | 6.0 GB | 8.6 GB | fits · 23.4 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · vantagewithai | 4.9 GB | 7.5 GB | fits · 24.5 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1.8 GB of working memory for Krea 2 and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Krea 2 on a RTX 5090 32 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 5090 32 GB
The RTX 5090 32 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still.
32 GB GDDR7 · 512-bit · 1792 GB/s · Blackwell. Everything that runs on it →
05Questions
How much VRAM does Krea 2 need?
Around 7.5 GB with the smallest file (Q2_K) and 15.7 GB with an 8-bit file (FP8). The full 16-bit file needs about 28.9 GB.
Which Krea 2 file should I download for the RTX 5090 32 GB?
16-bit (26.3 GB) from Comfy-Org/Krea-2.
FP8 or Q8_0 for Krea 2 on the RTX 5090 32 GB?
FP8 (13.1 GB): the RTX 5090 32 GB computes it natively, while Q8_0 (13.7 GB) is unpacked on the fly.
How much do I need to download for Krea 2 on the RTX 5090 32 GB?
31.8 GB: krea2_turbo_bf16.safetensors, qwen3vl_4b_fp8_scaled.safetensors, qwen_image_vae.safetensors.