What does your model need?
Find an open model, see the GPU memory it takes to run or fine-tune, and the cheapest GPU that fits.
652 models. Memory marked ~ is an estimate from the model's size. Prices are full price for one GPU in stock, without VAT.
| Model | Task | GPU memory | Cheapest GPU that fits | Parameters | Downloads | License |
|---|---|---|---|---|---|---|
| bge-small-en BAAI | Feature extraction | ~0.1 GB | €0.04/h RTX 3060 | 0B | 216.1K | MIT |
| Realistic_Vision_V5.1_noVAE SG161222 | Text to image | — | — | 0.9B | 214.9K | creativeml-openrail-m |
| VibeVoice-1.5B microsoft | Text to speech | — | — | 2.7B | 209.2K | MIT |
| controlnet-union-sdxl-1.0 xinsir | Text to image | — | — | 1.3B | 208.4K | Apache 2.0 |
| medgemma-1.5-4b-it google | Image text to text | ~9.6 GB | €0.09/h RTX 3080 | 4.3B | 206.7K | Other |
| higgs-audio-v2-tokenizer eustlb | Feature extraction | ~0.5 GB | €0.04/h RTX 3060 | 0.2B | 202.2K | — |
| jina-clip-v1 jinaai | Feature extraction | ~0.5 GB | €0.04/h RTX 3060 | 0.2B | 202K | Apache 2.0 |
| SapBERT-UMLS-2020AB-all-lang-from-XLMR cambridgeltl | Feature extraction | ~0.6 GB | €0.04/h RTX 3060 | 0.3B | 202K | — |
| pplx-embed-v1-0.6b perplexity-ai | Feature extraction | ~1.3 GB | €0.04/h RTX 3060 | 0.6B | 201.9K | MIT |
| Wan2.1-I2V-14B-480P Wan-AI | Image to video | — | — | 16.4B | 200.6K | Apache 2.0 |
| phonon-31m-en gradium | Text to speech | — | — | 0B | 196.3K | Apache 2.0 |
| Illustrious-xl-early-release-v0 OnomaAIResearch | Text to image | — | — | 2.6B | 194.2K | Other |
| nova-furry-xl-il-v120-sdxl John6666 | Text to image | — | — | 2.6B | 188.7K | Other |
| VibeVoice-Realtime-0.5B microsoft | Text to speech | — | — | 1B | 186.3K | MIT |
| bge-large-en BAAI | Feature extraction | ~0.7 GB | €0.04/h RTX 3060 | 0.3B | 184.4K | MIT |
| Qwen3.8-Flash-Next-NVFP4 nvidia | Image text to text | ~140 GB | — | 120B | 184K | Other |
| Qwen-Image-2.1-viggle-turbo Viggle | Text to image | — | — | 7.1B | 182.9K | Other |
| Wan2.2-T2V-A14B-Diffusers Wan-AI | Text to video | — | — | 14.3B | 172K | Apache 2.0 |
| Wan2.2-I2V-A14B-Diffusers Wan-AI | Image to video | — | — | 14.3B | 170.3K | Apache 2.0 |
| Qwen3-Embedding-4B unsloth | Feature extraction | ~9 GB | €0.09/h RTX 3080 | 4B | 168.6K | Apache 2.0 |
| Wan2.2-TI2V-5B-Diffusers Wan-AI | Text to video | — | — | 5B | 167.3K | Apache 2.0 |
| indic-parler-tts ai4bharat | Text to speech | — | — | 0.9B | 166.6K | Apache 2.0 |
| LocateAnything-3B nvidia | Image text to text | ~8.6 GB | €0.09/h RTX 3080 | 3.8B | 156.8K | Other |
| LCM_Dreamshaper_v7 SimianLuo | Text to image | — | — | 0.9B | 156.3K | MIT |
| Wan2.1-VACE-14B Wan-AI | Image to video | — | — | 17.3B | 155.6K | Apache 2.0 |