community-verified · measured pool data
Can the RX 6700 XT 12GB run gemma-4-12B-it?
Yes — community-measured at 37.8 tok/s (4 runs at 4-bit).
Verified single-stream runs on the RX 6700 XT 12GB 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 | 37.8 | — | — | 4,736 | llama.cpp |