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 |
|---|---|---|---|---|---|---|
| S5-nano maritaca-ai | Image text to text | ~10 GB | €0.13/h RTX 5070 | 4.7B | 581 | Apache 2.0 |
| mSlideOn lightonai | Feature extraction | ~0.8 GB | €0.04/h RTX 3060 | 0.3B | 571 | Apache 2.0 |
| LTX-2-19b-distilled rootonchair | Image to video | — | — | 18.9B | 564 | Other |
| Qwen3-ForcedAligner-Ultra 17slever17 | Automatic speech recognition | — | — | 0.9B | 563 | Apache 2.0 |
| Alpie_seed 169Pi | Image text to text | ~21 GB | €0.17/h RTX 3090 | 9.4B | 545 | Apache 2.0 |
| Kandinsky-6.0-Lite-5s-Diffusers kandinskylab | Image to video | — | — | 3.2B | 537 | MIT |
| SkyReels-V2-DF-1.3B-540P Skywork | Text to video | — | — | 1.4B | 474 | Other |
| Rumble-2-Flash Reson8 | Automatic speech recognition | — | — | 0.5B | 429 | — |
| NorthCUA-Mini beipo-ai | Image text to text | ~78 GB | €2.09/h RTX PRO 6000 | 35.1B | 427 | Apache 2.0 |
| Thinklite-27B Sparset | Image text to text | ~62 GB | €2.09/h RTX PRO 6000 | 27.8B | 401 | Apache 2.0 |
| dots.tts.edit dots-studio | Text to speech | — | — | 2.2B | 397 | Other |
| sayro-tts-1.7B uzlm | Text to speech | — | — | 1.9B | 395 | Other |
| pjit-21k Linum-AI | Text to image | — | — | 2.2B | 382 | Apache 2.0 |
| Taraneh-WLarge areffarhadi | Automatic speech recognition | — | — | 1.5B | 381 | MIT |
| Audio8-TTS-Realistic-0.6b-bf16 mlx-community | Text to speech | — | — | 0.6B | 368 | Apache 2.0 |
| LoCo-7B MuyaoYuan | Text generation | ~17 GB | €0.17/h RTX 3090 | 7.6B | 362 | MIT |
| Prism2 paige-ai | Feature extraction | ~10 GB | €0.09/h RTX 3080 | 4.5B | 310 | cc-by-nc-nd-4.0 |
| Silencio-2 BlueRoseLabs | Text to speech | — | — | 0B | 289 | CC BY 4.0 |
| Kimi-K3.1-Pro-pruned75 vllm-project | Image text to text | ~888 GB | — | 738B | 286 | Other |
| clip4clip-webvid150k Searchium-ai | Text to video | — | — | 0.2B | 275 | — |
| Motif-Video-2B Motif-Technologies | Text to video | — | — | 2B | 273 | Apache 2.0 |
| Klein-TTS-X1.5-Flash-Lite klein-ml | Text to speech | — | — | 0B | 273 | Apache 2.0 |
| ninada gnumanth | Text to speech | — | — | 0.1B | 252 | CC BY 4.0 |
| penclaw-Kimi-K3.1-pro-unrestricted audnai | Text generation | ~3171 GB | — | 2780B | 228 | Other |
| BAT-vit-b16-pretrainedAS2M lrauch | Feature extraction | ~0.2 GB | €0.04/h RTX 3060 | 0.1B | 226 | MIT |