Loading…
Loading…
Models / Ornith-1.0
5 models (9B to 397B) · ↓ 2.7M downloads a month · from $0.34/h on 2x RTX 5060 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 |
|---|---|---|---|---|
| Originalornith-ai/Ornith-1.0-9B | vLLM | 19 GB | 24.3 GB | $0.34/h 2x RTX 5060 Ti |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalornith-ai/Ornith-1.0-35B | vLLM | 70 GB | 81 GB | $0.89/h 2x Nvidia A40 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalornith-ai/Ornith-1.0-35B-FP8 | vLLM | 38 GB | 44.8 GB | $0.45/h Nvidia A40 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalornith-ai/Ornith-1.0-397B-FP8 | vLLM | 405 GB | 453.5 GB | $11.77/h 8x RTX PRO 6000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalornith-ai/Ornith-1.0-397B | vLLM | 794 GB | 885.1 GB | $44.03/h 8x Nvidia H200 |
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").