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 |
|---|---|---|---|---|---|---|
| full-duplex-speech-data-engine penguinfish1688 | Text to speech | — | — | 1.9B | 82 | CC BY-NC 4.0 |
| whisper-turbo-az hasan0v | Automatic speech recognition | — | — | 0.8B | 61 | Apache 2.0 |
| Kandinsky-S2V-1.0-Pro-Diffusers kandinskylab | Image to video | — | — | 21.4B | 55 | MIT |
| edu_jev-0.8B jiazhengli | Feature extraction | ~1.7 GB | €0.04/h RTX 3060 | 0.8B | 53 | CC BY-NC 4.0 |
| Kandinsky-6.0-Lite-pretrain-5s-Diffusers kandinskylab | Image to video | — | — | 3.2B | 51 | MIT |
| SD1.5-DALLE-2 snwy | Text to image | — | — | 0.9B | 49 | — |
| mettle-1.5 slideflow-labs | Feature extraction | ~2.5 GB | €0.04/h RTX 3060 | 1.1B | 46 | — |
| Vimoo-1.0 Vimoo-AI | Text to video | — | — | 11.7B | 38 | Apache 2.0 |
| stock-embed-mamba3 HamSession | Feature extraction | ~0 GB | €0.04/h RTX 3060 | 0B | 31 | Apache 2.0 |
| FLUX.2-klein-9B-Text-Encoder-Pruned-5.1B SearchingMan | Feature extraction | ~11 GB | €0.13/h RTX 5070 | 5.1B | 31 | Other |
| africa-tts AfriSpeech | Text to speech | — | — | 0.1B | 30 | CC BY-NC 4.0 |
| text-to-video-ms-1.7b vdo | Text to video | — | — | 1.4B | 27 | CC BY-NC 4.0 |
| AIdeaLab-VideoJP aidealab | Text to video | — | — | 1.7B | 25 | Apache 2.0 |
| Kimi-K3.1-Pro-Global-Pruned-37 nota-ai | Image text to text | ~2030 GB | — | 1759B | 20 | Other |
| Prism2-survival paige-ai | Feature extraction | ~1.4 GB | €0.04/h RTX 3060 | 0.6B | 17 | cc-by-nc-nd-4.0 |
| Wan2.2-TI2V-5B-ternary AsadIsmail | Text to video | — | — | 5B | 16 | Apache 2.0 |
| text-to-video-ms-1.7b Ruxy1212 | Text to video | — | — | 1.4B | 15 | CC BY-NC 4.0 |
| urdu-sukhan-asr-v1 Loudness-ai | Automatic speech recognition | — | — | 0.8B | 12 | CC BY-NC 4.0 |
| Kimi-K3.1-Pro-Global-Pruned-30 nota-ai | Image text to text | ~2247 GB | — | 1953B | 7 | Other |
| Hotshot-XL vdo | Text to video | — | — | 2.8B | 4 | OpenRAIL++ |
| Qwen3.8-40B-Ultimate-Heretic-Uncensored DavidAU | Image text to text | ~89 GB | €2.09/h RTX PRO 6000 | 40B | 3 | Apache 2.0 |
| pocket-tts-farsi-v2 mehdi-hf | Text to speech | — | — | 0.1B | 0 | CC BY-NC 4.0 |
| Irodori-TTS-v4.1-Small Aratako | Text to speech | — | — | 0.8B | 0 | MIT |
| ARC4_Encoder_Llama kyutai | Feature extraction | ~6.8 GB | €0.04/h RTX 3060 | 3B | 0 | CC BY 4.0 |
| nava-fa zorost | Text to speech | — | — | 0.1B | 0 | Other |