community pool / model answer
NVIDIA-Nemotron-3-Nano-4B-GGUF
chat · nvidia/NVIDIA-Nemotron-3-Nano-4B-GGUF
184 tok/s · model median · 4 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| RTX 5070 12GB | 4-bit | 182.2 tok/s | measured | 124 | 4.6 GB | 32,768 | llama.cpp |
| RTX 5090 32GB | 8-bit | 237.8 tok/s | reported | 34 | - GB | 2,048 | lmstudio |
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.