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 |
|---|---|---|---|---|---|---|
| ERNIE-Image baidu | Text to image | — | — | 8B | 2K | Apache 2.0 |
| ABot-World-0-5B-LF acvlab | Image to video | — | — | 5.3B | 1.9K | Apache 2.0 |
| Diffusion-Qwen3.8-27B summerAIO | Text generation | ~60 GB | €2.09/h RTX PRO 6000 | 26.9B | 1.9K | Apache 2.0 |
| signal-jepa braindecode | Feature extraction | ~0 GB | €0.04/h RTX 3060 | 0B | 1.7K | MIT |
| Apex-35B-V1.0 Apexintelligence-AI | Text generation | ~80 GB | €2.09/h RTX PRO 6000 | 36B | 1.7K | Apache 2.0 |
| reve-large brain-bzh | Feature extraction | ~0.9 GB | €0.04/h RTX 3060 | 0.4B | 1.7K | Other |
| ERNIE-5.5-Flash-Base baidu | Text generation | ~322 GB | — | 286B | 1.7K | Other |
| iris-3b speridlabs | Text to image | — | — | 3B | 1.7K | Apache 2.0 |
| FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree FastVideo | Text to video | — | — | 35B | 1.6K | Other |
| Qwen3.5-0.8B-Astra-WeightEdit JonathanColetti | Image text to text | ~2 GB | €0.04/h RTX 3060 | 0.9B | 1.6K | Apache 2.0 |
| Groot-19B-A3B-261023 GrootTeam | Image text to text | ~43 GB | €0.62/h RTX 6000 Ada | 19.4B | 1.6K | Apache 2.0 |
| Kandinsky-6.0-Lite-distill-5s-Diffusers kandinskylab | Image to video | — | — | 3.2B | 1.5K | MIT |
| Qwen3.8-27B-DSpine-b16 tencent | Text generation | ~4.5 GB | €0.04/h RTX 3060 | 2B | 1.5K | Apache 2.0 |
| Audio8-TTS-Preview-0.1b Edge0 | Text to speech | — | — | 0.2B | 1.4K | Other |
| DeepSeek-V4-Pro-Qwen3.5-9B Jackrong | Text generation | ~22 GB | €0.17/h RTX 3090 | 9.7B | 1.3K | Apache 2.0 |
| SenseNova-6.8-Code2Video sensenova | Image text to text | ~61 GB | €2.09/h RTX PRO 6000 | 27.4B | 1.3K | Apache 2.0 |
| pplx-embed-v2-context-0.6b perplexity-ai | Feature extraction | ~1.3 GB | €0.04/h RTX 3060 | 0.6B | 1.3K | — |
| mstyledistance StyleDistance | Feature extraction | ~0.6 GB | €0.04/h RTX 3060 | 0.3B | 1.3K | MIT |
| HunyuanImage-3.0 tencent | Text to image | — | — | 83B | 1.2K | Other |
| coder-lfm3-1.7b AJ-Gonzalez | Text generation | ~3.9 GB | €0.04/h RTX 3060 | 1.7B | 1.2K | Other |
| g-omnivoice g-group-ai-lab | Text to speech | — | — | 0.6B | 1.2K | Apache 2.0 |
| Qwen3.8-27B-Ultimate-Heretic-Uncensored DavidAU | Image text to text | ~62 GB | €2.09/h RTX PRO 6000 | 27.8B | 1.2K | Apache 2.0 |
| MNN-Pocket-0.3B taobao-mnn | Text generation | ~0.8 GB | €0.04/h RTX 3060 | 0.4B | 1.1K | Apache 2.0 |
| Axion-1.0-35B Axion1-0 | Text generation | ~78 GB | €2.09/h RTX PRO 6000 | 35.1B | 1.1K | Apache 2.0 |
| MERT-v2-30s m-a-p | Feature extraction | ~1.4 GB | €0.04/h RTX 3060 | 0.6B | 1.1K | CC BY-NC 4.0 |