community-verified · measured pool data
Can the RTX 3060 12GB ×2 run gemma-4-19b-a4b-it-REAP-GGUF?
Yes — community-measured at 77.5 tok/s (6 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 | 77.5 | 2028.8 | 12.9 GB | 32,768 | llama.cpp |