community-verified · measured pool data
Can the Multi-GPU 72GB ×3 run Laguna-S-2.1?
Yes — community-measured at 60.3 tok/s (5 runs at 4-bit).
Verified single-stream runs on the Multi-GPU 72GB ×3 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 | 60.3 | 326.8 | 65.1 GB | 278,528 | llama.cpp |