community-verified · measured pool data
Can the RTX 4070 12GB run gemma-4-26B-A4B-it?
Yes — community-measured at 20.4 tok/s (7 runs at 4-bit).
Verified single-stream runs on the RTX 4070 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 | 20.4 | 1661.1 | — | 2,048 | vllm |