community pool / model answer
Ornith-1.5-9B
chat · ornith-ai/Ornith-1.5-9B
73.5 tok/s · model median · 76 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| CMP 170HX 64GB | 16-bit | 72.8 tok/s | measured | 2,249 | - GB | 131,336 | sglang, vllm |
| RTX 2060 Super 8GB | 4-bit | 60.4 tok/s | reported | - | 5.4 GB | 8,192 | llama.cpp |
| RTX 5070 12GB | 4-bit | 102 tok/s | reported | 47 | - GB | 2,048 | llama.cpp |
| RX 570 4GB | 4-bit | 23 tok/s | measured | 43,198 | - GB | 2,048 | llama.cpp |
Context tested
The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.