community-verified · measured pool data
Can the RTX 3060 12GB ×2 run gemma-4-26B-A4B-it-GGUF?
Yes — community-measured at 68.6 tok/s (13 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 | 68.6 | 2495.4 | 18.6 GB | 131,072 | llama.cpp |