Page values for "DeepSeek V4.1 Flash on 2x 8 GB (Project Maya)"
From CMP Wiki
More actions
"Recipe" values
1 row is stored for this page| Field | Field type | Allowed values | Value |
|---|---|---|---|
| page | Page | DeepSeek V4.1 Flash on 2x 8 GB (Project Maya) | |
| model | String | DeepSeek-V4.1-Flash-1017 (748B in the Maya README) | |
| quant | String | Maya GGUF (Maya-S 340 GB or Maya-XS 277 GB; Engram tables stay on SSD) | |
| engine | String | Project Maya (Strata and llama.cpp lineage) | |
| engine_version | String | ||
| cards | String | 8 GB · 10 GB · both | 8 GB |
| card_count | Integer | 2 | |
| topology | String | engine-managed expert tiering across VRAM, host RAM and NVMe | |
| context | String | ||
| decode_tps | Float | 63.0 | |
| prefill_tps | Float | ||
| vram_per_card | String | 64 GB | |
| power_cap | String | ||
| driver | String | ||
| unlock_build | String | ||
| flags | Text | ||
| status | String | Proven · Reported · Theory · Contested · Warning | Reported |
| tested_by | String | pcsv. | |
| tested_on | Date | 2026-10-25 | |
| source | String | https://github.com/mw00/project-maya#how-fast-is-it | |
| files | Wikitext |