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 |
|---|---|---|---|---|---|---|
| drama-3 fishaudio | Text to speech | — | — | 35.9B | 44.9K | Other |
| Z-Image Tongyi-MAI | Text to image | — | — | 6.2B | 44.8K | Apache 2.0 |
| orpheus-3b-0.1-ft unsloth | Text to speech | — | — | 3.3B | 44.5K | Apache 2.0 |
| stable-video-diffusion-img2vid stabilityai | Image to video | — | — | 1.5B | 42.1K | Other |
| orpheus-3b-0.1-ft canopylabs | Text to speech | — | — | 3.8B | 41.9K | Apache 2.0 |
| LTX-2.5-FP8 unsloth | Text to video | — | — | 19B | 40.8K | Other |
| Wan2.1-VACE-1.3B Wan-AI | Image to video | — | — | 2.2B | 40.4K | Apache 2.0 |
| Qwen3.5-4B-GLB-3D-Coder ccore | Text generation | ~10 GB | €0.13/h RTX 5070 | 4.5B | 38.7K | Apache 2.0 |
| clef-flash Cloudflare | Image text to text | ~21 GB | €0.17/h RTX 3090 | 9.4B | 36.9K | Apache 2.0 |
| IndicF5 ai4bharat | Text to speech | — | — | 0.4B | 35.7K | MIT |
| krea-realtime-video krea | Text to video | — | — | 14.3B | 35.1K | Apache 2.0 |
| Qwen3.8-Flash-Next-FP4-Local nvidia | Image text to text | ~110 GB | — | 96.5B | 34.7K | Other |
| LTX-2.5-Diffusers Lightricks | Text to video | — | — | 19B | 34.6K | Other |
| TwIL-8B webAI-Official | Text generation | ~20 GB | €0.17/h RTX 3090 | 8.8B | 34.5K | Other |
| orukeet oruk | Automatic speech recognition | — | — | 0.6B | 33.9K | cc-by-sa-4.0 |
| animatediff-motion-adapter-v1-5-2 guoyww | Text to video | — | — | 0.5B | 33.8K | — |
| Zonos-v0.1-transformer Zyphra | Text to speech | — | — | 1.6B | 31.3K | Apache 2.0 |
| Audio8-ASR-0.1B Edge0 | Automatic speech recognition | — | — | 0.3B | 31K | CC BY-NC 4.0 |
| stable-virtual-camera stabilityai | Image to video | — | — | 1.3B | 30.4K | Other |
| SoulX-FlashTalk-14B Soul-AILab | Image to video | — | — | 18.9B | 28.8K | Apache 2.0 |
| VibeVoice-1.5B vibevoice | Text to speech | — | — | 2.7B | 28.5K | MIT |
| Evoke-Turbo AlayaLab | Text to video | — | — | 14.3B | 28.4K | Apache 2.0 |
| phonon-40m-de gradium | Text to speech | — | — | 0.1B | 28.2K | CC BY-NC 4.0 |
| Breeze-TTS-2 BreezeBlue | Text to speech | — | — | 3.5B | 26K | Other |
| Hydrogen-1.0 deep-principle | Text generation | ~1684 GB | — | 753B | 26K | MIT |