i2i 6GB 12GB 16GB fp8 gguf 4steps 20steps (Qwen2509 Workflow)

fp8 and gguf workflow (single image)

• Qwen2509_fp8_16GB_12GB_GGUF_6GB_4steps_v8 w/Lightning Lora

• Qwen2509_fp8_16GB_12GB_GGUF_6GB_20steps_v8

# VRAM usage (second pass)

- 16GB : fp8 (25 seconds on 4070tis @4steps)

- 12GB : fp8 w/DisTorch2MultiGPU

- 6GB : Q4gguf w/DisTorch2MultiGPU

- 16GB : Q4gguf

I'm uploading this because it was hard to find a workflow that doesn't use Lightning Lora.

(But Lightning 4steps is very good.)