Loading…
Loading…
Models / distilbert-base-multilingual-cased
1 model (~135M) · ↓ 881.3K 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 |
|---|---|---|---|---|
| Originaldistilbert/distilbert-base-multilingual-cased | ONNX Runtime | 910 MB | 2.4 GB | $0.08/h GTX 1660 SUPER |
| Namo Turn Detector v1 Korean (videosdk-live)videosdk-live/Namo-Turn-Detector-v1-Korean | ONNX Runtime | 140 MB | 1.2 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").