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 |
|---|---|---|---|---|---|---|
| Pika-H3-Flex Pika-Labs | Image to video | — | — | 33.1B | 1.1K | Other |
| FastVideo-FastH3-8-Step-V2 FastVideo | Text to video | — | — | 35B | 1.1K | Other |
| Minico-M1-1105 Mincofficial | Text generation | ~0.8 GB | €0.04/h RTX 3060 | 0.4B | 1.1K | Other |
| QUAN-Transcribe-1.0 qnguyen3 | Automatic speech recognition | — | — | 0.1B | 1K | Gemma |
| pplx-embed-v2-late-9b perplexity-ai | Feature extraction | ~19 GB | €0.17/h RTX 3090 | 8.4B | 1K | MIT |
| P-H3-Image PrunaAI | Text to image | — | — | 33.1B | 1K | Other |
| pplx-embed-v2-context-9b-preview perplexity-ai | Feature extraction | ~19 GB | €0.17/h RTX 3090 | 8.4B | 1K | MIT |
| VieNeu-TTS pnnbao-ump | Text to speech | — | — | 0.6B | 1K | Apache 2.0 |
| Oc-e-Non-v1 p-e-w | Text generation | ~9 GB | €0.09/h RTX 3080 | 4B | 947 | Apache 2.0 |
| debertinha-ptbr-xsmall sagui-nlp | Feature extraction | ~0.1 GB | €0.04/h RTX 3060 | 0B | 934 | MIT |
| Qwen3-8B-ZeroZero-Heretic LastMachine | Text generation | ~18 GB | €0.17/h RTX 3090 | 8.2B | 907 | Apache 2.0 |
| Qwen3.5-0.8B-weight-space-programming ML-Intern-lab | Image text to text | ~2 GB | €0.04/h RTX 3060 | 0.9B | 906 | Apache 2.0 |
| KURE-Sparse-nano nlpai-lab | Feature extraction | ~0.3 GB | €0.04/h RTX 3060 | 0.1B | 901 | Apache 2.0 |
| LemonDecider inclusionAI | Feature extraction | ~10 GB | €0.11/h RTX A4000 | 4.5B | 880 | Apache 2.0 |
| NorthCUA-Pro beipo-ai | Image text to text | ~887 GB | — | 397B | 811 | Apache 2.0 |
| i2vgen-xl ali-vilab | Text to video | — | — | 1.4B | 736 | MIT |
| UniPercept Thunderbolt215215 | Feature extraction | ~18 GB | €0.17/h RTX 3090 | 7.9B | 704 | Apache 2.0 |
| SlideOn lightonai | Feature extraction | ~0.4 GB | €0.04/h RTX 3060 | 0.2B | 695 | Apache 2.0 |
| pplx-embed-v2-context-9b perplexity-ai | Feature extraction | ~19 GB | €0.17/h RTX 3090 | 8.4B | 640 | MIT |
| Cosmos3-Super-Image2Video-4Step nvidia | Image to video | — | — | 64B | 627 | Other |
| embeddinggemma-GTAIDE-300m-2605 taide | Feature extraction | ~0.7 GB | €0.04/h RTX 3060 | 0.3B | 627 | Other |
| ERNIE-5.5-Flash-Base-BF16 baidu | Text generation | ~640 GB | — | 286B | 618 | Other |
| leokani-tts-7M milliwattlabs | Text to speech | — | — | 0B | 603 | Other |
| hima-asr Prahaladha | Automatic speech recognition | — | — | 0.5B | 594 | Other |
| LFM3-1.7B-abliterated orcarouter | Text generation | ~3.9 GB | €0.04/h RTX 3060 | 1.7B | 586 | Other |