publish
Llama 3.1
llama-3.1
Total tests10
Avg speed51.68 t/s
First token0.23 s
Providers1
Variants2
Variants
Showing 1-2 of 2 providers
| Variant | Speed | Latency | Tests |
|---|---|---|---|
 | 52.19 t/s | 0.23s | 5 |
| 51.18 t/s | 0.23s | 5 |
Recent test records
10 records| Time | Model | Speed | Latency |
|---|---|---|---|
| Aug 21, 12:17 AM | nvidia/llama-3.1-nemotron-70b-instruct | 52.14 t/s | 0.40s |
| Aug 21, 12:17 AM | nvidia/llama-3.1-nemotron-70b-instruct | 52.30 t/s | 0.17s |
| Aug 21, 12:17 AM |