Can the RTX 4090 24 GB run FLUX.1 [dev]?
Yes. FP8 fits on the RTX 4090 24 GB with 9.8 GB to spare.
FP8 (11.9 GB) needs about 14.2 GB in use, so 9.8 GB of the 24 GB stays free: room for a larger image, a LoRA or a ControlNet.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | flux1-dev-fp8-e4m3fn.safetensors FP8 · Kijai/flux-fp8 | models/diffusion_models | 11.9 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 | 17.4 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 →
02Every FLUX.1 dev file on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 23.8 GB | 26.1 GB | 2.1 GB too big | the original weights | Hugging Face → |
| FP8 ← SAFETENSORS · Kijai | 11.9 GB | 14.2 GB | fits · 9.8 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · city96 | 12.7 GB | 15.0 GB | fits · 9.0 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 9.9 GB | 12.2 GB | fits · 11.8 GB spare | very close to the original | Hugging Face → |
| Q5_K_S GGUF · city96 | 8.3 GB | 10.6 GB | fits · 13.4 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_S GGUF · city96 | 6.8 GB | 9.1 GB | fits · 14.9 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_S GGUF · city96 | 5.2 GB | 7.5 GB | fits · 16.5 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · city96 | 4.0 GB | 6.3 GB | fits · 17.7 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) “Prompt executed in 11.28 seconds” 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 | 11.28 s / image | — | 2025-12-28 | github.com → |
| reported | Q8_0 GGUF · 1024x1024 · 20 steps “15 seconds at the fastest to 17 seconds at the slowest on my RTX 4090 with Euler 20 Steps for 1024x1024 images” stated range 15-17 s; city96 ComfyUI-GGUF Q8 | 15 s / image | — | 2024-08-25 | github.com → |
| reported | fp8 (--fast) · 1024x1024 · 20 steps “Prompt executed in 10.01 seconds” ComfyUI 'RTX 4090 benchmarks - FLUX model' thread; OP settings 1024x1024, 20 steps; Aug 2024 ComfyUI/PyTorch 2.5 dev; FP8 with --fast, GPU at 2.52 GHz/875mV undervolt (9.07 s at 2. | 10.01 s / image | — | 2024-08-26 | github.com → |
Other people's numbers are copied as published, with a link. Send yours.
04About the RTX 4090 24 GB
The RTX 4090 24 GB is an Ada Lovelace GPU with hardware FP8, so ComfyUI can compute Comfy-Org's FP8 files natively: small and fast. (Plain FP8 files use FP8 maths with the --fast fp8_matrix_mult option.)
24 GB GDDR6X · 384-bit · 1008 GB/s · Ada Lovelace. 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 4090 24 GB?
FP8 (11.9 GB) from Kijai/flux-fp8.
FP8 or Q8_0 for FLUX.1 dev on the RTX 4090 24 GB?
FP8 (11.9 GB): the RTX 4090 24 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 4090 24 GB?
17.4 GB: flux1-dev-fp8-e4m3fn.safetensors, t5xxl_fp8_e4m3fn.safetensors, clip_l.safetensors, ae.safetensors.