Page values for "GLM 5.3 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 | GLM 5.3 Flash on 2x 8 GB (Project Maya) | |
| model | String | GLM-5.3-Flash (321B in the Maya README) | |
| quant | String | Maya-M GGUF (116 GB), every expert in VRAM; Maya-S (96.5 GB) and Maya-S24 (94.7 GB) also reported | |
| engine | String | Project Maya (Strata and llama.cpp lineage, EXL3 loading, DFlash2 drafter) | |
| engine_version | String | v1.0.6 (this row) | |
| cards | String | 8 GB · 10 GB · both | 8 GB |
| card_count | Integer | 2 | |
| topology | String | engine-managed split with expert tiering across VRAM, RAM and NVMe | |
| context | String | ||
| decode_tps | Float | 61.3 | |
| prefill_tps | Float | 514.0 | |
| vram_per_card | String | 64 GB | |
| power_cap | String | ||
| driver | String | ||
| unlock_build | String | ||
| flags | Text | ./maya.sh --bench (three greedy 256-token answers for decode, an 8K-token prompt for prefill) | |
| status | String | Proven · Reported · Theory · Contested · Warning | Reported |
| tested_by | String | ZackO2o | |
| tested_on | Date | ||
| source | String | https://github.com/mw00/project-maya#how-fast-is-it | |
| files | Wikitext |