community-verified · measured pool data
Can the RTX 3050 8GB run gemma-4-E4B-it-GGUF?
Yes — community-measured at 46.4 tok/s (2 runs at 5-bit).
Verified single-stream runs on the RTX 3050 8GB 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 |
|---|---|---|---|---|---|
| 5-bit | 46.4 | 168.5 | — | 128,000 | llama.cpp |