community-verified · measured pool data
Can the Arc Pro B60 24GB run Llama-3.2-1B-Instruct?
Yes — community-measured at 189.4 tok/s (2 runs at 8-bit).
Verified single-stream runs on the Arc Pro B60 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 |
|---|---|---|---|---|---|
| 8-bit | 189.4 | 64.2 | — | 4,096 | llama.cpp |