community-verified · measured pool data
Can the GTX 1060 3GB run granite-4.0-h-micro?
Yes — community-measured at 45.2 tok/s (4 runs at 4-bit).
Verified single-stream runs on the GTX 1060 3GB 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 | 45.2 | 3058 | 2.5 GB | 2,048 | llama.cpp |