community-verified · measured pool data
Can the RTX 3090 24GB run gemma-4-26B-A4B-it-qat-GGUF?
Yes — community-measured at 138.3 tok/s (18 runs at 4-bit).
Verified single-stream runs on the RTX 3090 24GB 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 | 138.3 | 3433 | 0 GB | 131,072 | llama.cpp |