FLUX.1-dev vs stable-diffusion-3.5-medium

FLUX.1-dev (11.9B parameters) and stable-diffusion-3.5-medium (2.5B parameters) side by side: the memory each needs at every precision, what it costs to run on a live GPU, and the context window, KV cache and license where they are published. Numbers are computed from the models' published specs; this page does not rank quality.

Side by side

FactFLUX.1-devstable-diffusion-3.5-medium
Parameters11.9B2.5B
Architecture––
LicenseFLUX.1 [dev] Non-Commercial License–
Published precisionBF16BF16
VRAM needed, As published26.6 GB5.5 GB
VRAM needed, FP813.3 GB2.8 GB
VRAM needed, INT46.7 GB1.4 GB
Cheapest live fit, As publishedRTX A6000 · $0.363/hrRTX 3070 · $0.088/hr
Cheapest live fit, FP8RTX 5060 Ti · $0.180/hrRTX 4070 · $0.154/hr
Cheapest live fit, INT4RTX 3070 · $0.088/hrRTX 3070 · $0.088/hr

VRAM is the weight size at each precision times a flat 1.2 overhead; see the methodology. The FP8 and INT4 rows need a quantized checkpoint or an engine that quantizes on load. The fit is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

Which to pick

  • stable-diffusion-3.5-medium needs less VRAM at its published precision (5.5 GB against 26.6 GB), so it fits on a smaller GPU.
  • stable-diffusion-3.5-medium has the cheaper live GPU fit at its published precision ($0.088/hr against $0.363/hr).

These follow only from the facts in the table above. Whether either model does your task well is a separate question this page does not answer.

Keep reading

Other comparisons

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.