community-verified · measured pool data
Can the RTX 3060 12GB ×2 run InternVL3-38B?
Yes — community-measured at 15.8 tok/s (7 runs at 4-bit).
Verified single-stream runs on the RTX 3060 12GB ×2 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 | 15.8 | — | 0.1 GB | 16,384 | llama.cpp |