community pool / model answer
NVIDIA-Nemotron-3-Nano-4B-BF16
chat · nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
100 tok/s · model median · 64 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB | 4-bit | 93.2 tok/s | measured | 1,080 | - GB | 131,072 | llama.cpp |
| RTX 3060 Ti 8GB | 4-bit | 112.5 tok/s | measured | 1,809 | 3.9 GB | 131,072 | llama.cpp |
| RTX 3090 24GB | 4-bit | 160.3 tok/s | measured | 1,709 | 0 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.