Loading…
Loading…
Models / Ming-Lite-Omni
GPU memory needed (smallest version of each): Ming-Lite-Omni ~18.9B about 1 GB. The cheapest runs on GTX 1660 SUPER from $0.08/h right now.
1 model (~18.9B) · ↓ 1.7K downloads a month · from $0.08/h on GTX 1660 SUPER right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| 1.5inclusionAI/Ming-Lite-Omni-1.5 | ONNX Runtime | 30 MB | 1 GB | $0.08/h GTX 1660 SUPER |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. 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").