70B
1 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3090 | 70B 70B | EXL2 2.5bpw | ExLlamaV2 | 20 | – | – | – | – | 2023-10 | 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 3090 | 70B 70B | EXL2 2.5bpw | ExLlamaV2 | 20 | – | – | – | – | 2023-10 | community | – | source |