community-verified · measured pool data
Can the RTX3060+RTX2080-pooled-20GB 20GB run Llama-3.1-8B-Instruct?
Yes — community-measured at 105 tok/s (2 runs at 4-bit).
Verified single-stream runs on the RTX3060+RTX2080-pooled-20GB 20GB 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 | — | 5 GB | 2,048 | ollama |