live · 166 benchmarks tracked
Will it run on your GPU?
Community benchmarks for self-hosting open-weights AI models. Real speed numbers, real peak-VRAM, real consumer hardware. No vendor marketing.
§02·latest · recipes
- imageadvanced24GB+
FLUX 3 Image Klein on RX 7900 XTX: Distilled int8 in ComfyUI on ROCm 7.2.4 (Untested)
- imageintermediate8GB+
FLUX 3 Image Klein on RTX 3090 Ti: Distilled int8 Text-to-Image in ComfyUI
- imageintermediate8GB+
FLUX 3 Image Klein on RTX 3090: int8 Setup That Needs No FP8 in ComfyUI v0.41.2
- imageintermediate8GB+
FLUX 3 Image Klein on RTX 5080: Distilled int8 Plus the NVFP4 File in ComfyUI
- imageintermediate8GB+
FLUX 3 Image Klein on RTX 5070 Ti: ComfyUI int8 Setup and the Blackwell NVFP4 File
- imageintermediate8GB+
FLUX 3 Image Klein on RTX 5060 Ti: Distilled int8 in ComfyUI With an NVFP4 Option
§03·contribute
Ran a benchmark?
Share the numbers.
Drop a GPU, a model, and the numbers you measured. A source link — a forum post, a gist, a screenshot — helps us cross-check before the entry shows up in the dataset.
open dataCC BY-SA
Submit a benchmark