community-verified · measured pool data
Can the RTX 3090 24GB ×4 run NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4?
Yes — community-measured at 50.9 tok/s (2 runs at 4-bit).
Verified single-stream runs on the RTX 3090 24GB ×4 from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.
| Quantization | Median tok/s | TTFT (ms) | Peak VRAM | Max context tested | Engines |
|---|---|---|---|---|---|
| 4-bit | 50.9 | — | 21 GB | 65,536 | llama.cpp |