AI claims that are circulating but not officially confirmed. Each has a status and a timeline of dated sources, and stays here after it is confirmed or debunked.
| Status | Rumor | Last checked |
|---|---|---|
| Unconfirmed | Is it true that tODO(en): Code and tool calls can peak up to 275 tok/s - Reasoning traces up to 190 tok/s Hardware: 5080 16GB PCIe gen5x16, 64 DDR5 6400, Core Ultra 9 285K https://github.com/jesdga95/basalt Some PRs for the optimizations under my name are still pending (xyehya) but upstream already have solid gains & memory optimizations?TODO(en): [Update Benchmark] Basalt's new PRs (Strata fork) new record IQ3_S Qwen3.8 Flash Next on single RTX 5080 and 5 · TODO(en): [Update Benchmark] Basalt's new PRs (Strata fork) new record IQ3_S Qwe | · TODO(en): [Update Benchmark] Basalt's new PRs (Strata fork) new record IQ3_S Qwe |
We record what sources show, with dates. We don't predict or score how likely a rumor is.