community pool / model answer
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
chat · nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
93 tok/s · model median · 12 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| Arc Pro B70 32GB | 4-bit | 93 tok/s | measured | - | - GB | 16,384 | llama.cpp, vllm |
| H100 80GB | 16-bit | 381.2 tok/s | reported | 68 | 72.4 GB | 32,768 | vllm |
| H200 SXM 141GB | 16-bit | 337.6 tok/s | reported | 56 | 127.8 GB | 32,768 | vllm |
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.