Loading…
Loading…
Models / Ling-3.0-tiny
1 model (~7.89B) · ↓ 10.8K downloads a month · from $0.08/h on GTX 1080 Ti 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 |
|---|---|---|---|---|
| OriginalinclusionAI/Ling-3.0-tiny | vLLM | 16 GB | 21.6 GB | $0.16/h 2x RTX 3060 |
| ONNX (webbrain-one)webbrain-one/Ling-3.0-tiny-ONNX | ONNX Runtime GenAI | 4.8 GB | 9.5 GB | $0.08/h GTX 1080 Ti |
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").