image model · flux · Windows
Can I run FLUX.1 dev on Nvidia GeForce GTX 1070 (8GB)?
Yes. FLUX.1 dev runs on Nvidia GeForce GTX 1070 (8GB) at Q4 GGUF (~6.5 GB of ~7 GB usable).
Fits at Q4 GGUF (~6.5 GB of ~7 GB usable) but with little headroom. Close other apps to free a little VRAM before generating.
- Peak VRAM
- ~6.5 GB
- Usable on device
- ~7 GB
- Device memory
- 8 GB
- Quant
- Q4 GGUF
How to run it
Use ComfyUI or Draw Things at Q4 GGUF. The big text encoder is loaded to encode your prompt, then offloaded before generation, which is why peak VRAM stays near the backbone size rather than the sum of every file.
- Type
- image (DIT)
- Parameters
- 12B
- Peak VRAM
- ~6.5 GB at Q4 GGUF
- Resolution
- 1024×1024
- License
- FLUX.1-dev Non-Commercial License
- Memory
- 8 GB vram
- Usable for weights
- ~7 GB
- Power draw
- ~150 W
- Best runtime
- llama.cpp CUDA (Pascal, no tensor cores)
You could also run
Run FLUX.1 dev on other hardware
FAQ
Can Nvidia GeForce GTX 1070 (8GB) run FLUX.1 dev?
Yes. FLUX.1 dev runs on Nvidia GeForce GTX 1070 (8GB) at Q4 GGUF (~6.5 GB of ~7 GB usable).
How much VRAM does FLUX.1 dev need?
It is a tight fit on Nvidia GeForce GTX 1070 (8GB). At Q4 GGUF the realistic peak is ~6.5 GB of VRAM, versus ~33 GB with every component kept resident (no offload). With aggressive CPU offload it drops to ~3 GB, much slower.
What do I use to run FLUX.1 dev locally?
FLUX.1 dev runs in ComfyUI or Draw Things (among others). It loads as a diffusion checkpoint plus its text encoder and VAE, not a single chat command.
Sources
VRAM figures are sourced peak-usage anchors at the noted quant, validated 2026-09-14. See methodology.