1,000 models · refreshed nightly
Models that run on RTX 4070 · 16 GB
Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.
| # | Model | Params | Context | Commercial use | 30d | On RTX 4070 · 16 GB |
|---|---|---|---|---|---|---|
| 551 | stable-diffusion-3.5-large-controlnet-depth | 2.2 B | — | other | 41 K | 10.3 GB |
| 552 | Juggernaut-XI-v11 | — | — | ✗ cc-by-nc-nd-4.0 | 41 K | 8.3 GB |
| 553 | stable-diffusion-3.5-large-controlnet-canny | 2.2 B | — | other | 41 K | 10.3 GB |
| 554 | Z-Image-Turbo-GGUF | — | — | ✓ apache-2.0 | 39 K | 4.7 GB |
| 555 | Chroma-GGUF-All-Versions | — | — | ✓ apache-2.0 | 38 K | 6.0 GB |
| 556 | flux2-klein-9b-uncensored-text-encoder | 8.2 B | — | other | 38 K | 7.3 GB |
| 557 | Anima-2.9B | — | — | other | 37 K | 10.3 GB |
| 558 | controlnet-scribble-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 36 K | 3.4 GB |
| 559 | Qwen-Image-GGUF | — | — | ✓ apache-2.0 | 35 K | 8.4 GB |
| 560 | zimage_turbo_training_adapter | — | — | ✓ apache-2.0 | 34 K | 1.1 GB |
| 561 | Qwen-Image-Edit-Rapid-AIO-GGUF | — | — | ✓ apache-2.0 | 34 K | 8.7 GB |
| 562 | Krea2-realism-V2 | — | — | ✓ mit | 34 K | 2.2 GB |
| 563 | z-image-turbo-nsfw-v2-GGUF | — | — | ✓ apache-2.0 | 33 K | 8.4 GB |
| 564 | autismmix-sdxl-autismmix-pony-sdxl | 2.6 B | — | other | 32 K | 8.5 GB |
| 565 | FLUX.2-klein-9B-GGUF | — | — | unknown | 32 K | 6.7 GB |
| 566 | Krea2-Turbo-Distill-4step-LoRA | — | — | other | 32 K | 11.1 GB |
| 567 | Real-Qwen-Image-V2 | — | — | ✓ apache-2.0 | 31 K | 14.9 GB |
| 568 | stable-diffusion-v1-5-GGUF | — | — | ⚠ creativeml-openrail-m | 31 K | 2.2 GB |
| 569 | controlnet-depth-sdxl-1.0 | 1.3 B | — | ⚠ openrail++ | 31 K | 8.9 GB |
| 570 | minecraft-skin-generator-sdxl | 2.6 B | — | ⚠ openrail | 30 K | 14.2 GB |
| 571 | FLUX.1-dev-GGUF | — | — | other | 30 K | 4.9 GB |
| 572 | FLUX.2-klein-4B-GGUF | — | — | ✓ apache-2.0 | 29 K | 3.2 GB |
| 573 | flux2-klein-9b-uncensored-text-encoder-Q8_0-GGUF | — | — | other | 29 K | 10.1 GB |
| 574 | Krea2-Turbo-HD-V1 | — | — | other | 29 K | 9.5 GB |
| 575 | controlnet-canny-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 29 K | 6.2 GB |
| 576 | pony-diffusion-v6-xl-GGUF | — | — | ⚠ creativeml-openrail-m | 28 K | 3.6 GB |
| 577 | nunchaku-flux.1-schnell | — | — | ✓ apache-2.0 | 28 K | 15.6 GB |
| 578 | mlx-FLUX.1-schnell-4bit-quantized | — | — | ✓ apache-2.0 | 28 K | 8.2 GB |
| 579 | pony-v7-base | 6.9 B | — | other | 28 K | 5.9 GB |
| 580 | SenseNova-U1.5-8B_GGUFs | 8.0 B | — | ✓ apache-2.0 | 27 K | 11.9 GB |
| 581 | LLaDa-Image-Turbo_ComfyUI | — | — | unknown | 27 K | 10.6 GB |
| 582 | Flux_Lustly.ai_Uncensored_nsfw_v1 | — | — | ⚠ creativeml-openrail-m | 26 K | 0.9 GB |
| 583 | controlnet-canny-sdxl-1.0 | 1.3 B | — | ⚠ openrail++ | 26 K | 8.9 GB |
| 584 | picx-real | 860 M | — | ⚠ openrail | 25 K | 3.6 GB |
| 585 | flux-klein-9b-Biglove-Collection | — | — | ✗ cc-by-nc-4.0 | 24 K | 7.6 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.