Models

Popular models from Hugging Face that GridPup can serve, grouped by family and size, with the GPU memory each one needs and the cheapest machine that fits it right now. Open a family to compare its sizes and versions (the original, quantized and ONNX versions need less GPU memory) and the GPUs for each.

3,133 families · catalog updated 12:56 UTC

• firefunction by fireworks-aiText generation · 1 model · ↓ 119~46.7B
  Smallest needs107.2 GB GPU
  From$2.36/h4x Nvidia A40
• QwQ by huihui-aiText generation · 1 model · ↓ 11932B
  Smallest needs77.4 GB GPU
  From$0.89/hNvidia A100
• Arch-Function by katanemoText generation · 1 model · ↓ 1193B
  Smallest needs9.4 GB GPU
  From$0.09/hRTX 3060
• VideoGuard-Qwen3.5 by prithivMLmodsVideo + text · 2 models · ↓ 1184B9B
  Smallest needs14.7 GB GPU
  From$0.17/hRTX 5060 Ti
• miniG by CausalLMText generation · 1 model · ↓ 117~14B
  Smallest needs39.3 GB GPU
  From

Model details come from Hugging Face and are refreshed daily. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090"). Only machines with a Vast reliability above 95% that download at 400 Mbit/s or more are counted.