Can the RTX 5060 Ti 16 GB run FLUX.1 [dev]?
Timed on my own card, not estimated: 36.4 seconds per 1024x1024 image with the FP8 file, peaking at 14.8 GB.
FP8 (11.9 GB) fits with only 1.8 GB to spare (about 14.2 GB of 16 GB).
01My measurements
| Label | Setup | Result | Peak VRAM | Date | Source |
|---|---|---|---|---|---|
| measured | flux1-dev-Q8_0.gguf · 1024x1024 · 20 steps 3 timed runs after 1 warm-up (50.7 s incl. loading). T5-XXL FP8 + CLIP-L, euler/simple, guidance 3.5, ComfyUI 0.25.0 portable, PyTorch 2.12 cu130, 32 GB RAM. Time = sampling + VAE | 40.62 s / image | 15.1 GB | 2026-09-27 | |
| measured | flux1-dev-Q4_K_S.gguf · 1024x1024 · 20 steps 3 timed runs after 1 warm-up (52.1 s incl. loading). T5-XXL FP8 + CLIP-L, euler/simple, guidance 3.5, ComfyUI 0.25.0 portable, PyTorch 2.12 cu130, 32 GB RAM. Time = sampling + VAE | 47.28 s / image | 8.8 GB | 2026-09-27 | |
| measured | flux1-dev-fp8.safetensors · 1024x1024 · 20 steps 3 timed runs after 1 warm-up (39.1 s incl. loading). T5-XXL FP8 + CLIP-L, euler/simple, guidance 3.5, ComfyUI 0.25.0 portable, PyTorch 2.12 cu130, 32 GB RAM. Time = sampling + VAE | 36.36 s / image | 14.8 GB | 2026-09-27 | |
| reported | fp8 (ComfyUI template) “Prompt executed in 25.71 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; poster's log shows 16311 | 25.71 s / image | — | 2025-08-04 | github.com → |
Other people's numbers are copied as published, with a link. Send yours.
02What 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 →
03Every FLUX.1 dev file on 16 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · black-forest-labs | 23.8 GB | 26.1 GB | 10.1 GB too big | the original weights | Hugging Face → |
| FP8 ← SAFETENSORS · Kijai | 11.9 GB | 14.2 GB | fits · 1.8 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · city96 | 12.7 GB | 15.0 GB | fits · 1.0 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 9.9 GB | 12.2 GB | fits · 3.8 GB spare | very close to the original | Hugging Face → |
| Q5_K_S GGUF · city96 | 8.3 GB | 10.6 GB | fits · 5.4 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_S GGUF · city96 | 6.8 GB | 9.1 GB | fits · 6.9 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_S GGUF · city96 | 5.2 GB | 7.5 GB | fits · 8.5 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · city96 | 4.0 GB | 6.3 GB | fits · 9.7 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.
04Questions
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 5060 Ti 16 GB?
FP8 (11.9 GB) from Kijai/flux-fp8.
FP8 or Q8_0 for FLUX.1 dev on the RTX 5060 Ti 16 GB?
FP8 (11.9 GB): the RTX 5060 Ti 16 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 5060 Ti 16 GB?
17.4 GB: flux1-dev-fp8-e4m3fn.safetensors, t5xxl_fp8_e4m3fn.safetensors, clip_l.safetensors, ae.safetensors.