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 |
|---|---|---|---|---|---|---|
| penclaw-GLM-5.3-abliterated audnai | Text generation | ~1684 GB | — | 753B | 3.5K | Other |
| qwen3_asr_1.7b_ko TeamUNIVA | Automatic speech recognition | — | — | 2.3B | 3.5K | Apache 2.0 |
| stable-video-diffusion-img2vid-xt-1-1 stabilityai | Image to video | — | — | 1.5B | 3.5K | Other |
| Qwen3.5-0.8B-weight-space-programming RikiyaT | Image text to text | ~2 GB | €0.04/h RTX 3060 | 0.9B | 3.5K | Apache 2.0 |
| Arabic-Triplet-Matryoshka-V2 Omartificial-Intelligence-Space | Feature extraction | ~0.3 GB | €0.04/h RTX 3060 | 0.1B | 3.4K | Apache 2.0 |
| WeMM-Embedding-9B tencent | Feature extraction | ~21 GB | €0.17/h RTX 3090 | 9.4B | 3.3K | Other |
| phonon-refiner-1.7b Infatoshi | Text generation | ~3.9 GB | €0.04/h RTX 3060 | 1.7B | 3K | Other |
| VoiceTut-TTS mohammedaly22 | Text to speech | — | — | 0.6B | 3K | Apache 2.0 |
| Hemmingway-1.5 HemmingwayAI | Text generation | ~61 GB | €2.09/h RTX PRO 6000 | 27.3B | 3K | CC BY-NC 4.0 |
| pplx-embed-v2-late-0.6b perplexity-ai | Feature extraction | ~1.3 GB | €0.04/h RTX 3060 | 0.6B | 2.9K | MIT |
| Voxtral-Mini-4B-Realtime-Arabic mistralai | Automatic speech recognition | — | — | 4.4B | 2.9K | — |
| pplx-embed-context-v1-0.6b perplexity-ai | Feature extraction | ~1.3 GB | €0.04/h RTX 3060 | 0.6B | 2.8K | MIT |
| AREX-2 BAAI | Image text to text | ~61 GB | €2.09/h RTX PRO 6000 | 27.4B | 2.8K | Apache 2.0 |
| NeoMME-260M Hcompany | Feature extraction | ~0.6 GB | €0.04/h RTX 3060 | 0.3B | 2.6K | Apache 2.0 |
| lumi-4b ceia-br | Text generation | ~8.9 GB | €0.09/h RTX 3080 | 4B | 2.6K | — |
| LTX-Video-0.9.8-13B-distilled Lightricks | Image to video | — | — | 13B | 2.5K | Other |
| GLiDE-27B fastino | Image text to text | ~58 GB | €2.09/h RTX PRO 6000 | 26.1B | 2.5K | Other |
| Fibo-2.0-dev briaai | Text to image | — | — | 8.1B | 2.5K | Other |
| Arete-27B NousResearch | Text generation | ~61 GB | €2.09/h RTX PRO 6000 | 27.4B | 2.4K | Apache 2.0 |
| Qwen3.8-cyber-RedTeam-Surgical-Abliterated medismera | Text generation | ~31 GB | €0.62/h RTX 6000 Ada | 27.4B | 2.3K | Apache 2.0 |
| Terminal-RSI-27B Teriminal-RSI | Text generation | ~62 GB | €2.09/h RTX PRO 6000 | 27.8B | 2.3K | Apache 2.0 |
| Qwen3.5-4B-Qwenputer divagr1925 | Text generation | ~21 GB | €0.17/h RTX 3090 | 9.4B | 2.2K | Apache 2.0 |
| SunflowerASR-51-african-languages Sunbird | Automatic speech recognition | — | — | 1.5B | 2.2K | Apache 2.0 |
| LTX-Video-0.9.7-distilled Lightricks | Text to video | — | — | 13B | 2.1K | Other |
| whisper-large-v3-turbo-sk kinit | Automatic speech recognition | — | — | 0.8B | 2K | MIT |