Qwen3.8 Flash Next on 1x 8 GB (iIIusi0n SSD PLE)/Confirmation 2
From CMP Wiki
More actions
| Confirms | Qwen3.8 Flash Next on 1x 8 GB (iIIusi0n SSD PLE) |
|---|---|
| Result | Reproduced |
| By | @dottoreargus |
| Date | 2026-10-07 |
| Cards | 8 GB |
| Numbers | 5K+ tok/s prefill on a single 8 GB card after tuning. |
Changes on top of the repo: prefill batch 2,048 to 4,096, MTP draft tokens 1 to 2, PLE row cache 512 to 8,192 MiB, PLE AIO queue depth 256 to 512; NDIV 67, +250 MHz core offset, 200 W. He warns measurement differences may explain part of the gap. Used for one to two weeks of reverse-engineering work without issues. Source: @dottoreargus, 2026-10-07