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 |
|---|---|---|---|---|---|---|
| Qwen3.5-2B Qwen | Image text to text | ~5.1 GB | €0.04/h RTX 3060 | 2.3B | 3.7M | Apache 2.0 |
| Qwen3-1.7B Qwen | Text generation | ~4.5 GB | €0.04/h RTX 3060 | 2B | 3.7M | Apache 2.0 |
| Qwen3.5-0.8B Qwen | Image text to text | ~2 GB | €0.04/h RTX 3060 | 0.9B | 3.5M | Apache 2.0 |
| OmniVoice k2-fsa | Text to speech | — | — | 0.6B | 3.5M | — |
| pythia-160m EleutherAI | Text generation | ~0.5 GB | €0.04/h RTX 3060 | 0.2B | 3.5M | Apache 2.0 |
| OTel-2.0-Decision-26B-A4B-4bit farbodtavakkoli | Text generation | ~58 GB | €2.09/h RTX PRO 6000 | 25.8B | 3.2M | Apache 2.0 |
| bge-small-zh-v1.5 BAAI | Feature extraction | ~0.1 GB | €0.04/h RTX 3060 | 0B | 3.1M | MIT |
| Qwen3.8-27B-MLX-4bit lmstudio-community | Image text to text | ~61 GB | €2.09/h RTX PRO 6000 | 27.4B | 3M | Apache 2.0 |
| Qwen3-32B Qwen | Text generation | ~73 GB | €2.09/h RTX PRO 6000 | 32.8B | 3M | Apache 2.0 |
| Qwen3.8-27B-MLX-8bit lmstudio-community | Image text to text | ~61 GB | €2.09/h RTX PRO 6000 | 27.4B | 2.9M | Apache 2.0 |
| Qwen3.8-27B-MLX-6bit lmstudio-community | Image text to text | ~61 GB | €2.09/h RTX PRO 6000 | 27.4B | 2.9M | Apache 2.0 |
| Qwen3.8-27B-MLX-5bit lmstudio-community | Image text to text | ~61 GB | €2.09/h RTX PRO 6000 | 27.4B | 2.9M | Apache 2.0 |
| parakeet-tdt-0.6b-v3 mlx-community | Automatic speech recognition | — | — | 0.6B | 2.7M | CC BY 4.0 |
| DeepSeek-V4-Flash-0731 deepseek-ai | Text generation | ~342 GB | — | 304B | 2.7M | MIT |
| bge-base-en BAAI | Feature extraction | ~0.2 GB | €0.04/h RTX 3060 | 0.1B | 2.7M | MIT |
| Qwen2.5-3B-Instruct Qwen | Text generation | ~6.9 GB | €0.04/h RTX 3060 | 3.1B | 2.6M | Other |
| Qwen3-4B-Instruct-2507 Qwen | Text generation | ~9 GB | €0.09/h RTX 3080 | 4B | 2.6M | Apache 2.0 |
| SmolLM2-135M HuggingFaceTB | Text generation | ~0.3 GB | €0.04/h RTX 3060 | 0.1B | 2.5M | Apache 2.0 |
| tiny-Qwen3ForCausalLM trl-internal-testing | Text generation | ~0 GB | €0.04/h RTX 3060 | 0B | 2.5M | — |
| Qwen3-Embedding-4B Qwen | Feature extraction | ~9 GB | €0.09/h RTX 3080 | 4B | 2.5M | Apache 2.0 |
| mms-300m-1130-forced-aligner MahmoudAshraf | Automatic speech recognition | — | — | 0.3B | 2.4M | CC BY-NC 4.0 |
| Qwen3.6-27B Qwen | Image text to text | ~62 GB | €2.09/h RTX PRO 6000 | 27.8B | 2.3M | Apache 2.0 |
| moondream2 vikhyatk | Image text to text | ~4.3 GB | €0.04/h RTX 3060 | 1.9B | 2.3M | Apache 2.0 |
| mxbai-embed-large-v1 mixedbread-ai | Feature extraction | ~0.7 GB | €0.04/h RTX 3060 | 0.3B | 2.3M | Apache 2.0 |
| tiny-Qwen2ForCausalLM-2.5 trl-internal-testing | Text generation | ~0 GB | €0.04/h RTX 3060 | 0B | 2.3M | — |