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 |
|---|---|---|---|---|---|---|
| romanian-wav2vec2 gigant | Automatic speech recognition | — | — | 0.3B | 1.2M | Apache 2.0 |
| Qwen2.5-0.5B Qwen | Text generation | ~1.1 GB | €0.04/h RTX 3060 | 0.5B | 1.2M | Apache 2.0 |
| LTX-Video Lightricks | Image to video | — | — | 1.9B | 1.2M | Other |
| Hy3 tencent | Text generation | ~668 GB | — | 299B | 1.2M | Apache 2.0 |
| OTel-2.0-LLM-31B-IT-QLoRA farbodtavakkoli | Text generation | ~70 GB | €2.09/h RTX PRO 6000 | 31.3B | 1.2M | Apache 2.0 |
| DeepSeek-V4-Flash deepseek-ai | Text generation | ~327 GB | — | 291B | 1.2M | MIT |
| gemma-4-26B-A4B-it-AWQ-4bit cyankiwi | Image text to text | ~58 GB | €2.09/h RTX PRO 6000 | 25.8B | 1.1M | Apache 2.0 |
| Gemma-4-31B-IT-NVFP4 nvidia | Text generation | ~47 GB | €0.62/h RTX 6000 Ada | 20.9B | 1.1M | Other |
| Qwen2.5-14B-Instruct-AWQ Qwen | Text generation | ~33 GB | €0.62/h RTX 6000 Ada | 14.8B | 1.1M | Apache 2.0 |
| wav2vec2-large-xlsr-korean kresnik | Automatic speech recognition | — | — | 0.3B | 1.1M | Apache 2.0 |
| Qwen3-0.6B PrimeIntellect | Text generation | ~1.7 GB | €0.04/h RTX 3060 | 0.8B | 1.1M | Apache 2.0 |
| Qwen3.8-27B-AWQ-INT4 cyankiwi | Image text to text | ~62 GB | €2.09/h RTX PRO 6000 | 27.8B | 1.1M | Apache 2.0 |
| Qwen3-30B-A3B Qwen | Text generation | ~68 GB | €2.09/h RTX PRO 6000 | 30.5B | 1.1M | Apache 2.0 |
| Ornith-1.5-9B-NVFP4 ornith-ai | Text generation | ~9.4 GB | €0.09/h RTX 3080 | 6.7B | 1.1M | MIT |
| Ornith-1.5-35B-A3B-NVFP4 ornith-ai | Text generation | ~24 GB | €0.17/h RTX 3090 | 19.5B | 1.1M | MIT |
| Qwen3-VL-2B-Instruct Qwen | Image text to text | ~4.8 GB | €0.04/h RTX 3060 | 2.1B | 1.1M | Apache 2.0 |
| wav2vec2-large-xls-r-300m-Urdu kingabzpro | Automatic speech recognition | — | — | 0.3B | 1.1M | Apache 2.0 |
| Qwen3-Coder-30B-A3B-Instruct-FP8 Qwen | Text generation | ~35 GB | €0.62/h RTX 6000 Ada | 30.5B | 1.1M | Apache 2.0 |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 nvidia | Text generation | ~74 GB | €2.09/h RTX PRO 6000 | 32.9B | 1.1M | Other |
| NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 nvidia | Text generation | ~1253 GB | — | 561B | 1.1M | Other |
| MiniCPM5-2B openbmb | Text generation | ~5.6 GB | €0.04/h RTX 3060 | 2.5B | 1.1M | Apache 2.0 |
| GLM-4.7-Flash zai-org | Text generation | ~70 GB | €2.09/h RTX PRO 6000 | 31.2B | 1M | MIT |
| stable-diffusion-v1-5 stable-diffusion-v1-5 | Text to image | — | — | 0.9B | 1M | creativeml-openrail-m |
| NVIDIA-Nemotron-3-Super-120B-A12B-BF16 nvidia | Text generation | ~276 GB | — | 124B | 1M | Other |
| wav2vec2-xls-r-parlaspeech-hr classla | Automatic speech recognition | — | — | 0.3B | 1M | — |