community-verified · measured pool data
Can the RTX 3090 24GB ×2 run gemma-4-26B-A4B-it?
Yes — community-measured at 154.1 tok/s (2 runs at 8-bit).
Verified single-stream runs on the RTX 3090 24GB ×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 |
|---|---|---|---|---|---|
| 8-bit | 154.1 | 42.5 | 45.3 GB | 262,144 | vllm |