A2000
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| A2000 | llama 7B | Q4_0 | llama.cpp (CUDA) | 51.96 | 1411.42 | – | – | tg128 | 2025-08-23 | community | – | source |
| A2000 | llama 7B | Q4_0 | llama.cpp (CUDA) | 51.21 | 1259.66 | – | – | tg128 | 2025-08-23 | community | – | source |
| A2000 | llama 7B | Q4_0 | llama.cpp (CUDA) | 45.69 | 1361.85 | – | – | tg128 | 2025-08-23 | community | – | source |
| A2000 | llama 7B | Q4_0 | llama.cpp (CUDA) | 45.52 | 1245.19 | – | – | tg128 | 2025-08-23 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085