community-verified · measured pool data
Can the RTX 3060 Ti 8GB run Qwen3-8B?
Yes — community-measured at 53 tok/s (26 runs at 4-bit).
Verified single-stream runs on the RTX 3060 Ti 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 |
|---|---|---|---|---|---|
| 4-bit | 53 | 1205.8 | 7.5 GB | 65,536 | llama.cpp |