Can the RTX 5090 32 GB run FLUX.1 [dev]?
Yes. 16-bit fits on the RTX 5090 32 GB with 5.9 GB to spare.
Take 16-bit (23.8 GB). In use it comes to about 26.1 GB, with 5.9 GB left over on 32 GB.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux1-dev.safetensors 16-bit · black-forest-labs/FLUX.1-dev | models/diffusion_models | 23.8 GB | Download → |
| Text encoder | t5xxl_fp8_e4m3fn.safetensors T5-XXL FP8 · comfyanonymous/flux_text_encoders | models/text_encoders | 4.9 GB | Download → |
| Text encoder | clip_l.safetensors CLIP-L · comfyanonymous/flux_text_encoders | models/text_encoders | 0.2 GB | Download → |
| VAE | ae.safetensors FLUX.1 VAE (ae) · Comfy-Org/Lumina_Image_2.0_Repackaged | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 29.3 GB | |||
Alternatives: T5-XXL FP16 (9.8 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: FP8 workflow (.json) · GGUF Q8_0 workflow (.json). Drag the file into ComfyUI. All workflows →
System RAM: 48 GB or more. These files take about 29.3 GB of RAM while loaded, 35.3 GB with Windows and ComfyUI. What happens with less. calculated
02Every FLUX.1 dev file on 32 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · black-forest-labs | 23.8 GB | 26.1 GB | fits · 5.9 GB spare | the original weights | Hugging Face → |
| FP8 SAFETENSORS · Kijai | 11.9 GB | 14.2 GB | fits · 17.8 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · city96 | 12.7 GB | 15.0 GB | fits · 17.0 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 9.9 GB | 12.2 GB | fits · 19.8 GB spare | very close to the original | Hugging Face → |
| Q5_K_S GGUF · city96 | 8.3 GB | 10.6 GB | fits · 21.4 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_S GGUF · city96 | 6.8 GB | 9.1 GB | fits · 22.9 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_S GGUF · city96 | 5.2 GB | 7.5 GB | fits · 24.5 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · city96 | 4.0 GB | 6.3 GB | fits · 25.7 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1.5 GB of working memory for FLUX.1 dev and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
| Label | Setup | Result | Peak VRAM | Date | Source |
|---|---|---|---|---|---|
| reported | fp8 (ComfyUI template) “Getting 8.78s at 2.38it/s for 3 runs.” ComfyUI 'GPU Benchmark Flux DEV fp8' thread: stock Flux dev fp8 workflow template, time of 2nd/3rd run (no loading); resolution/steps not stated in thread; Inno3D RTX 5090 X3 OC | 8.78 s / image · 2.38 it/s | — | 2025-08-05 | github.com → |
Other people's numbers are copied as published, with a link. Send yours.
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 FLUX.1 dev need?
Around 6.3 GB with the smallest file (Q2_K) and 14.2 GB with an 8-bit file (FP8). The full 16-bit file needs about 26.1 GB.
Which FLUX.1 dev file should I download for the RTX 5090 32 GB?
16-bit (23.8 GB) from black-forest-labs/FLUX.1-dev.
FP8 or Q8_0 for FLUX.1 dev on the RTX 5090 32 GB?
FP8 (11.9 GB): the RTX 5090 32 GB computes it natively, while Q8_0 (12.7 GB) is unpacked on the fly.
How much do I need to download for FLUX.1 dev on the RTX 5090 32 GB?
29.3 GB: flux1-dev.safetensors, t5xxl_fp8_e4m3fn.safetensors, clip_l.safetensors, ae.safetensors.