community pool / model answer
Nemotron-Cascade-14B-Thinking
chat · nvidia/Nemotron-Cascade-14B-Thinking
34.2 tok/s · model median · 18 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB ×2 | 4-bit | 29.7 tok/s | measured | 3,817 | 15.4 GB | 131,072 | llama.cpp |
| RTX 3090 24GB | 4-bit | 44.5 tok/s | measured | 2,668 | - GB | 131,072 | 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.