llama 3B
1 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 | llama 3B | Q4_K - Medium | llama.cpp (Metal) | 45.95 | 530.01 | – | – | tg128 | 2026-05-12 | community | – | source |
1 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 | llama 3B | Q4_K - Medium | llama.cpp (Metal) | 45.95 | 530.01 | – | – | tg128 | 2026-05-12 | community | – | source |