Page values for "Qwen3.8 Flash Next on 2x 8 GB (Plean PP2)"
From CMP Wiki
More actions
"Recipe" values
1 row is stored for this page| Field | Field type | Allowed values | Value |
|---|---|---|---|
| page | Page | Qwen3.8 Flash Next on 2x 8 GB (Plean PP2) | |
| model | String | Qwen3.8-Flash-Next | |
| quant | String | Mixed INT4 AutoRound (Minachist/Qwen3.8-Flash-Next-INT4-Mixed-AutoRound, about 65 GB) with the full BF16 PLE table on NVMe | |
| engine | String | vLLM 0.29.1rc1 nightly plus the checkpoint author's patches | |
| engine_version | String | ||
| cards | String | 8 GB · 10 GB · both | 8 GB |
| card_count | Integer | 2 | |
| topology | String | PP2, MTP 3, no P2P | |
| context | String | 262,144 (256K in the post) | |
| decode_tps | Float | 197.0 | |
| prefill_tps | Float | 5,800.0 | |
| vram_per_card | String | 64 GB | |
| power_cap | String | ||
| driver | String | ||
| unlock_build | String | ||
| flags | Text | --pipeline-parallel-size 2, MTP 3 draft tokens, max concurrency 6, BF16 PLE table offloaded to NVMe | |
| status | String | Proven · Reported · Theory · Contested · Warning | Reported |
| tested_by | String | plean. | |
| tested_on | Date | 2026-10-07 | |
| source | String | https://www.bozocentral.com/2x-cmp170hx-qwen3-flash-next | |
| files | Wikitext |