community-verified · measured pool data
Can the Ryzen AI Max 395 64GB run gemma-4-E2B-it-GGUF?
Yes — community-measured at 105.6 tok/s (4 runs at 4-bit).
Verified single-stream runs on the Ryzen AI Max 395 64GB 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 | 105.6 | 532.5 | 3.8 GB | 8,192 | llama.cpp |