Home
AI
Bench
Measured on real home PCs
Compare
GPU results
Method
Notes
Lab notes
What we tried on home GPUs, including the runs that failed and how we fixed them.
Partly worked
2026-10-24
FLUX.3 [klein] on a 12 GB RTX 5070: four tries, one clean run
FLUX.3 klein came out in October 2026. It needs a newer ComfyUI than the container image we use, so each rented node updates ComfyUI to v0.42.1 at start-up.
Worked
2026-10-24
FLUX.2 [klein] 4B: about 3 seconds on a 12 GB card
FLUX.2 klein 4B (Apache-2.0) runs in 4 steps at cfg 1.
Failed, then fixed
2026-10-23
Z-Image Turbo did not fit a 16 GB card in our setup
Z-Image Turbo (Apache-2.0) is a 12.3 GB model plus an 8 GB text encoder.
Failed, then fixed
2026-10-23
The 0.1-second trap: ComfyUI caches identical jobs
Our first warm runs reported about 0.1 s per image. That was not a fast GPU.