P102-100
4 records across 1 models (quants: Q4_0).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| P102-100 | llama 7B | Q4_0 | llama.cpp (CUDA) | 49.59 | 1032.13 | – | – | tg128 | 2026-10-01 | community | – | source |
| P102-100 | llama 7B | Q4_0 | llama.cpp (CUDA) | 49.08 | 1029.43 | – | – | tg128 | 2026-10-01 | community | – | source |
| P102-100 | llama 7B | Q4_0 | llama.cpp (CUDA) | 46.77 | 935.02 | – | – | tg128 | 2026-10-01 | community | – | source |
| P102-100 | llama 7B | Q4_0 | llama.cpp (CUDA) | 46.45 | 927.54 | – | – | tg128 | 2026-10-01 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085