community-verified · measured pool data
Can the RX 570 4GB ×2 run Mellum2-12B-A2.5B-Instruct?
Yes — community-measured at 62.7 tok/s (2 runs at 4-bit).
Verified single-stream runs on the RX 570 4GB ×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 |
|---|---|---|---|---|---|
| 4-bit | 62.7 | 95.1 | — | 2,048 | llama.cpp |