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 |
|---|---|---|---|---|---|---|
| MOSS-TTS-Local-Transformer OpenMOSS-Team | Text to speech | — | — | 3.1B | 151.4K | Apache 2.0 |
| jina-embeddings-v2-base-code jinaai | Feature extraction | ~0.4 GB | €0.04/h RTX 3060 | 0.2B | 146.7K | Apache 2.0 |
| miewid-msv3 conservationxlabs | Feature extraction | ~0.1 GB | €0.04/h RTX 3060 | 0.1B | 139.2K | — |
| mimi kyutai | Feature extraction | ~0.2 GB | €0.04/h RTX 3060 | 0.1B | 137.1K | CC BY 4.0 |
| canine-c google | Feature extraction | ~0.3 GB | €0.04/h RTX 3060 | 0.1B | 136.2K | Apache 2.0 |
| granite-speech-4.1-2b-nar ibm-granite | Feature extraction | ~5 GB | €0.04/h RTX 3060 | 2.3B | 133.1K | Apache 2.0 |
| GLM-5.3-CYBERSECURITY-FP8 dealignai | Text generation | ~844 GB | — | 753B | 129.6K | MIT |
| granite-embedding-97m-multilingual-r2 ibm-granite | Feature extraction | ~0.2 GB | €0.04/h RTX 3060 | 0.1B | 126.8K | Apache 2.0 |
| FLUX.1-schnell unsloth | Text to image | — | — | 11.9B | 122.1K | Apache 2.0 |
| stable-video-diffusion-img2vid-xt stabilityai | Image to video | — | — | 1.5B | 120.8K | Other |
| mxbai-embed-2d-large-v1 mixedbread-ai | Feature extraction | ~0.7 GB | €0.04/h RTX 3060 | 0.3B | 120K | Apache 2.0 |
| higgs-tts-3-4b bosonai | Text to speech | — | — | 4.7B | 119.6K | Other |
| jina-embeddings-v2-base-en arkohut | Feature extraction | ~0.3 GB | €0.04/h RTX 3060 | 0.1B | 109.8K | Apache 2.0 |
| janku-v5-nsfw-trained-noobai-rou-wei-illustrious-xl-v50-sdxl John6666 | Text to image | — | — | 2.6B | 108K | Other |
| Krea-2-Raw krea | Text to image | — | — | 12.8B | 106.5K | Other |
| harrier-oss-v1-270m microsoft | Feature extraction | ~0.6 GB | €0.04/h RTX 3060 | 0.3B | 106.4K | MIT |
| Wan2.1-I2V-14B-720P-Diffusers Wan-AI | Image to video | — | — | 16.4B | 106.3K | Apache 2.0 |
| bge-small-en-v1.5 michaelfeil | Feature extraction | ~0.1 GB | €0.04/h RTX 3060 | 0B | 104K | MIT |
| FastWan2.2-TI2V-5B-FullAttn-Diffusers FastVideo | Text to video | — | — | 5B | 103.2K | Apache 2.0 |
| Wan2.1-T2V-14B-Diffusers Wan-AI | Text to video | — | — | 14.3B | 102.7K | Apache 2.0 |
| cohere-transcribe-03-2026 CohereLabs | Automatic speech recognition | — | — | 2.1B | 102.7K | Apache 2.0 |
| Wan2.1-T2V-14B Wan-AI | Text to video | — | — | 14.3B | 102.3K | Apache 2.0 |
| sopro-v2-turbo samuel-vitorino | Text to speech | — | — | 0.1B | 101.7K | Apache 2.0 |
| Wan2.1-I2V-14B-480P-Diffusers Wan-AI | Image to video | — | — | 16.4B | 101.3K | Apache 2.0 |
| HunyuanDiT-v1.1-Diffusers-Distilled Tencent-Hunyuan | Text to image | — | — | 1.5B | 101.2K | Other |