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 |
|---|---|---|---|---|---|---|
| FastWan-QAD-FP8-1.3B FastVideo | Text to video | — | — | 1.4B | 190 | Apache 2.0 |
| parakeet-tdt-0.6b-v3-uk ihnatov-yuri | Automatic speech recognition | — | — | 0.6B | 176 | CC BY 4.0 |
| Klein-TTS-X1.5-Pro klein-ml | Text to speech | — | — | 0B | 169 | Apache 2.0 |
| Pika-H3-Flex-NVFP4-QAD FastVideo | Image to video | — | — | 13.9B | 165 | Other |
| chroma-h3 lodestones | Text to image | — | — | 33.1B | 151 | Other |
| Drishya-Tiny udgamlabs | Text to video | — | — | 0.2B | 139 | CC BY-NC 4.0 |
| LLaDA-MoE-v2-30B-A3B-Instruct GSAI-ML | Feature extraction | ~71 GB | €2.09/h RTX PRO 6000 | 31.8B | 137 | Apache 2.0 |
| AuroraIMG2-100M AuroraAI-Research | Text to image | — | — | 0.1B | 135 | Apache 2.0 |
| clap2-large-audioxl-s1B laion | Feature extraction | ~0.8 GB | €0.04/h RTX 3060 | 0.3B | 133 | Apache 2.0 |
| Nemotron-3.5-Transcribe-kk-v2 Sherkhan243 | Automatic speech recognition | — | — | 33.7B | 129 | Other |
| PINT nyralabs | Feature extraction | ~0.2 GB | €0.04/h RTX 3060 | 0.1B | 122 | CC BY-NC 4.0 |
| DM-JEPA DangerLabs | Feature extraction | ~0.7 GB | €0.04/h RTX 3060 | 0.3B | 118 | MIT |
| Boldt-Embed-DE-350M mayflowergmbh | Feature extraction | ~1 GB | €0.04/h RTX 3060 | 0.4B | 117 | Apache 2.0 |
| FastVideo-Minimax-FastH3-Preview-v0.2 FastVideo | Text to video | — | — | 35B | 117 | Other |
| Kandinsky-S2V-1.0-Pro-distill-Diffusers kandinskylab | Image to video | — | — | 21.4B | 107 | MIT |
| omnivoice-urdu-3h mlwithabdullah | Text to speech | — | — | 0.6B | 106 | Apache 2.0 |
| hyper3-clip-v1 hyper3labs | Feature extraction | ~0.3 GB | €0.04/h RTX 3060 | 0.1B | 104 | openmdw-1.0 |
| VoxMedic-turbo-beta lion-ai | Automatic speech recognition | — | — | 0.8B | 104 | Other |
| Kandinsky-S2V-1.0-Lite-distill-Diffusers kandinskylab | Image to video | — | — | 2.3B | 100 | MIT |
| Klein-TTS-X1.5-Flash klein-ml | Text to speech | — | — | 0B | 99 | Apache 2.0 |
| voicetut-egyptian-tashkeel masterofaudio2077 | Text to speech | — | — | 0.6B | 99 | Apache 2.0 |
| NTv3_pretrained InstaDeepAI | Feature extraction | ~1.6 GB | €0.04/h RTX 3060 | 0.7B | 93 | Other |
| splade-ettin-encoder-17m-gooaq capemox | Feature extraction | ~0 GB | €0.04/h RTX 3060 | 0B | 93 | MIT |
| html-lm Seznam | Feature extraction | ~0.3 GB | €0.04/h RTX 3060 | 0.2B | 91 | CC BY-NC 4.0 |
| bge-small-rrf-v2 Stffens | Feature extraction | ~0.1 GB | €0.04/h RTX 3060 | 0B | 90 | Apache 2.0 |