Page values for "Qwen3.8 Flash Next on 2x 8 GB (mannydelrio 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 (mannydelrio PP2) | |
| model | String | Qwen3.8-Flash-Next-Uncensored (refusal-removed, from orcarouter) | |
| quant | String | AWQ W4A16 g32 (leoncca/Qwen3.8-Flash-Next-Uncensored-AWQ-g32); PLE table converted to INT4 and served from SSD | |
| engine | String | wtdcode/vllm-backport 3142ded1 plus a two-file patch and two tinybeast PLE plugins (venv, no container) | |
| engine_version | String | vllm-backport 3142ded1 | |
| cards | String | 8 GB · 10 GB · both | 8 GB |
| card_count | Integer | 2 | |
| topology | String | PP2 (layer partition 25,23), no P2P | |
| context | String | 262,144 | |
| decode_tps | Float | 177.8 | |
| prefill_tps | Float | 7,006.0 | |
| vram_per_card | String | 64 GB, --gpu-memory-utilization 0.94, TB_TORCH_MEM_CAP_GIB=61.5 | |
| power_cap | String | 180 W | |
| driver | String | nvidia-open 610.43.02 + cmpunlocker v0.5 or newer | |
| unlock_build | String | cmpunlocker v0.5+ (sudo ./install.sh --profile=8gb --no-iommu) | |
| flags | Text | '"`UNIQ--nowiki-0000004A-QINU`"' | |
| status | String | Proven · Reported · Theory · Contested · Warning | Reported |
| tested_by | String | mrmannyatx | |
| tested_on | Date | 2026-10-15 | |
| source | String | https://github.com/mannydelrio/qwen38-flash-next-2x-cmp170hx | |
| files | Wikitext |