community pool / model answer
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF
chat · ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF
128.9 tok/s · model median · 100 runs in the model record.
| Reference rig | Quantization | Median result | Basis | TTFT (ms) | Peak VRAM | Max context | Engines |
|---|---|---|---|---|---|---|---|
| CMP 170HX 64GB | 8-bit | 138.7 tok/s | measured | 8,362 | - GB | 67,592 | llama.cpp |
| RTX 3090 24GB | 4-bit | 353.7 tok/s | reported | 262 | 21.4 GB | 8,192 | llama.cpp |
| RX 7900 XT 20GB ×2 | 4-bit | 115.6 tok/s | measured | 73 | - 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.