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 |
|---|---|---|---|---|---|---|
| LTX-Video-0.9.5 Lightricks | Text to video | — | — | 1.9B | 11.3K | Other |
| Qwen-Image-2.1-Lightning-v2-RL lightx2v | Text to image | — | — | 7.1B | 10.5K | Other |
| parakeet-rnnt-1.1b nvidia | Automatic speech recognition | — | — | 1.1B | 10.5K | CC BY 4.0 |
| animatediff-motion-adapter-v1-5-3 guoyww | Text to video | — | — | 0.4B | 10.5K | — |
| Liquid-Codec LiquidAI | Feature extraction | ~0.2 GB | €0.04/h RTX 3060 | 0.1B | 10.3K | Other |
| Wan-Move-14B-480P Ruihang | Image to video | — | — | 16.4B | 10.3K | Apache 2.0 |
| d1-2B LiquidAI | Image text to text | ~4.3 GB | €0.04/h RTX 3060 | 1.9B | 10.1K | Other |
| parakeet-redux moondream | Automatic speech recognition | — | — | 0.1B | 10.1K | CC BY 4.0 |
| medasr google | Automatic speech recognition | — | — | 0.1B | 9.9K | Other |
| drama-3-int4 fishaudio | Text to speech | — | — | 6.9B | 9.6K | Other |
| VerseCrafter TencentARC | Image to video | — | — | 17.3B | 9.5K | Other |
| granite-speech-5.0-2b ibm-granite | Automatic speech recognition | — | — | 2.3B | 9.4K | Apache 2.0 |
| C-RADIOv4-H nvidia | Feature extraction | ~1.5 GB | €0.04/h RTX 3060 | 0.7B | 8.7K | Other |
| DeepSeek-V4.1-Flash-1017-NVFP4 nvidia | Image text to text | ~745 GB | — | 665B | 8.5K | MIT |
| Ming-3.0-tts-tiny inclusionAI | Text to speech | — | — | 9B | 8.5K | MIT |
| CogVideoX-5b zai-org | Text to video | — | — | 5.6B | 8.4K | Other |
| NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-FP8 nvidia | Automatic speech recognition | — | — | 33.7B | 8.3K | Other |
| maya1 maya-research | Text to speech | — | — | 3.3B | 8.2K | Apache 2.0 |
| SkyReels-V2-DF-14B-720P Skywork | Text to video | — | — | 14.3B | 7.9K | Other |
| SkyReels-V2-T2V-14B-720P Skywork | Text to video | — | — | 14.3B | 7.8K | Other |
| harrier-oss-v1-27b microsoft | Feature extraction | ~60 GB | €2.09/h RTX PRO 6000 | 27B | 7.2K | MIT |
| DeepSeek-V4.1-Flash-1017-obliterated OBLITERATUS | Text generation | ~1687 GB | — | 755B | 7K | MIT |
| HunyuanVideo-1.5-Diffusers-480p_t2v hunyuanvideo-community | Text to video | — | — | 8.3B | 7K | Other |
| CogVideoX-5b-I2V zai-org | Image to video | — | — | 5.6B | 6.9K | Other |
| DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic xtools-at | Text generation | ~10 GB | €0.13/h RTX 5070 | 4.7B | 6.8K | Apache 2.0 |