Back to models
publish

Llama 3.3

llama-3.3

Avg speed
838.52t/s
First token
0.39s
Total tests
30
Providers
4
Variants
4

Variants

Showing 1-4 of 4 providers

VariantSpeedLatencyTests
1133.81 t/s
0.45s
20
Hugging Face
416.19 t/s
0.26s
5
integrate.api.nvidia.com

Recent test records

20 records
TimeModelSpeedLatency
Jan 14, 02:25 AMmeta-llama/Llama-3.3-70B-Instruct
450.56 t/s
0.28s
Jan 14, 02:25 AMmeta-llama/Llama-3.3-70B-Instruct
363.23 t/s
0.25s
Jan 14, 02:25 AMmeta-llama/Llama-3.3-70B-Instruct
79.68 t/s
0.28s
5
Veloerallama-3.3-70b
-
-s
0
336.89 t/s
0.26s
Jan 14, 02:25 AMmeta-llama/Llama-3.3-70B-Instruct
391.98 t/s
0.24s
Jan 14, 02:25 AMmeta-llama/Llama-3.3-70B-Instruct
538.29 t/s
0.27s
Dec 25, 02:02 PMllama-3.3-70b
1982.40 t/s
0.30s
Dec 25, 02:02 PMllama-3.3-70b
1527.80 t/s
0.25s
Dec 25, 02:02 PMllama-3.3-70b
1528.56 t/s
0.15s
Dec 25, 02:02 PMllama-3.3-70b
964.64 t/s
0.25s
Dec 25, 02:02 PMllama-3.3-70b
1659.34 t/s
0.32s
Nov 8, 12:45 PMnvidia/llama-3.3-nemotron-super-49b-v1.5
79.98 t/s
0.56s
Nov 8, 12:45 PMnvidia/llama-3.3-nemotron-super-49b-v1.5
78.27 t/s
0.16s
Nov 8, 12:45 PMnvidia/llama-3.3-nemotron-super-49b-v1.5
79.79 t/s
0.19s
Nov 8, 12:45 PMnvidia/llama-3.3-nemotron-super-49b-v1.5
81.13 t/s
0.30s
Nov 8, 12:45 PMnvidia/llama-3.3-nemotron-super-49b-v1.5
79.22 t/s
0.20s
Sep 21, 06:19 PMllama-3.3-70b
1027.16 t/s
0.44s
Sep 21, 06:19 PMllama-3.3-70b
1189.55 t/s
0.42s
Sep 21, 06:19 PMllama-3.3-70b
1143.17 t/s
0.37s
Sep 21, 06:19 PMllama-3.3-70b
947.97 t/s
0.89s
Sep 21, 06:19 PMllama-3.3-70b
1005.61 t/s
0.45s
llama-3.3-70b
meta-llama/Llama-3.3-70B-Instruct
nvidia/llama-3.3-nemotron-super-49b-v1.5