Updated 2026-10-15 · ranked by real download data
Commercial-use image models
Ranked nightly from our download snapshots of the Hugging Face catalog. Every entry shows its licence and what hardware it realistically needs.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 01 | Z-Image-Turbo-GGUF +4 variants | — | — | ✓ apache-2.0 | 1.1 M | from 4.5 GB |
| 02 | FLUX.1-schnell +2 variants | 11.9 B | — | ✓ apache-2.0 | 574 K | from 65.9 GB |
| 03 | Qwen-Image-2512-GGUF +1 variant | — | — | ✓ apache-2.0 | 322 K | from 8.6 GB |
| 04 | Qwen-Image-Lightning | — | — | ✓ apache-2.0 | 273 K | from 72.6 GB |
| 05 | Qwen-Image +2 variants | 20.4 B | — | ✓ apache-2.0 | 272 K | from 67.0 GB |
| 06 | Qwen-Image-2.1-Turbo-Uncensored-GGUF | 8.8 B | — | ✓ apache-2.0 | 258 K | from 5.5 GB |
| 07 | Z-Image-Lora +5 variants | 6.2 B | — | ✓ apache-2.0 | 253 K | from 113.3 GB |
| 08 | Qwen-Image-2512-Lightning | — | — | ✓ apache-2.0 | 162 K | from 118.7 GB |
| 09 | LCM_Dreamshaper_v7 | 860 M | — | ✓ mit | 156 K | from 10.4 GB |
| 10 | ERNIE-Image-Turbo-GGUF | — | — | ✓ apache-2.0 | 152 K | from 4.7 GB |
| 11 | controlnet-openpose-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 147 K | from 6.2 GB |
| 12 | controlnet-union-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 137 K | from 6.2 GB |
| 13 | Z-Image-GGUF +1 variant | — | — | ✓ apache-2.0 | 125 K | from 4.9 GB |
| 14 | NetaYume-Lumina-Image-2.0 | — | — | ✓ apache-2.0 | 112 K | from 99.5 GB |
| 15 | Chroma-GGUF | — | — | ✓ apache-2.0 | 93 K | from 6.0 GB |
| 16 | nunchaku-qwen-image-edit | — | — | ✓ apache-2.0 | 85 K | from 162.9 GB |
| 17 | InstantID | — | — | ✓ apache-2.0 | 75 K | from 3.3 GB |
| 18 | FLUX.2-klein-4B-mflux-4bit | — | — | ✓ apache-2.0 | 73 K | from 5.6 GB |
| 19 | Chroma1-HD | 8.9 B | — | ✓ apache-2.0 | 65 K | from 51.7 GB |
| 20 | girlslike-zimage | 6.2 B | — | ✓ apache-2.0 | 60 K | from 8.4 GB |
| 21 | FLUX.2-klein-4B-GGUF | — | — | ✓ apache-2.0 | 60 K | from 3.2 GB |
| 22 | girlslike-krea2 | 12.8 B | — | ✓ apache-2.0 | 60 K | from 7.8 GB |
| 23 | z-image-turbo-nsfw-v2-GGUF | — | — | ✓ apache-2.0 | 59 K | from 8.4 GB |
| 24 | Z-Image-Loras | — | — | ✓ apache-2.0 | 59 K | from 90.1 GB |
| 25 | HiDream-I1-Fast | 17.1 B | — | ✓ mit | 54 K | from 55.0 GB |
Membership and ranking refresh nightly after the snapshot run. VRAM is an estimate for the smallest quantization at 8K context — methodology.