Tier list
Local AI model tier list
Every model we track, ranked by quality alone. Tiers don’t depend on your hardware: they tell you how capable a model is. To see which ones your machine can run, use the Model Finder.
How the 61 image models stack up
Who makes the best ones · models rated A or A+
Step 1
Tell us your hardware first
Then you will see how many of these 61 image models run on it, and can filter the list by how well each one runs.
Excellent · scores 85–100
Best in class: the results people choose these models for.
- Fibo 2.0 Dev 93
- MiniMax H3 Image 93
- Qwen-Image 2.1 93
- Krea 2 Turbo 93
- Cosmos3-Super Text2Image (64B) 92
- FLUX.2 [dev] 92
- Ideogram 4 92
- FLUX 3 Image Klein 91
- HunyuanImage 3.0 (80B-A13B) 90
- Qwen-Image 2512 90
- Qwen-Image 2.1 Turbo 89
- ERNIE-Image 88
- Qwen-Image 88
- FireRed-Image-Edit 1.1 87
- Ming-Image 0.1 Design 86
- Qwen-Image-Edit 2511 86
- ERNIE-Image Turbo 85
Great · scores 70–84
Great: close to the best, often lighter or faster.
Good · scores 55–69
Good: dependable for most everyday jobs.
- OmniGen2 66
- Stable Diffusion 3.5 Large 66
- Juggernaut XL v9 62
- Lumina-Image 2.0 62
- RealVisXL V5.0 62
- Stable Diffusion 3.5 Large Turbo 62
- Animagine XL 4.0 60
- Illustrious XL v0.1 60
- Kolors 60
- Playground v2.5 60
- AuraFlow v0.3 58
- DreamShaper XL v2 Turbo 58
- Pony Diffusion V6 XL 58
- Stable Diffusion 3.5 Medium 58
- Animagine XL 3.1 56
- Stable Diffusion XL 1.0 55
Fair · scores 40–54
Fair: usable, with visible limits.
Basic · scores under 40
Basic: older or very small models.
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.