Includes 694 hourly rounds up to 2026-11-16 from NIMStats by Mauro Druwel (source), measured with a different prompt and timeout. Our own probe adds a round every 30 minutes.
nemotron-3-super-120b-a12b
Downnvidia/nemotron-3-super-120b-a12b did not answer any probe on the NVIDIA NIM free API in the last 24 hours.
Model vs. median
Against the median of models that answered, last 24 hours.
nemotron-3-super-120b-a12b median of answering models
Error breakdown
0 failed of 0 probes, last 24 hours.
No failed probes in this range.
Time to first token
Each probe. Lower is better.
No probe was answered in this range, so there is no latency to plot.
Throughput
Tokens per second after the first token, each probe. Higher is better.
No answered probe in this range.
Availability heatmap
Last 7 days by UTC hour.
all answered some failed none answered not probed
Run history
Last 20 probes.
No probes in this range.
Call nemotron-3-super-120b-a12b
The endpoint is OpenAI-compatible.
Create a free key at build.nvidia.com, then:
curl https://integrate.api.nvidia.com/v1/chat/completions \
-H "Authorization: Bearer $NVIDIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-super-120b-a12b",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 256,
"stream": true
}'Other models answering
Top of the leaderboard right now.
- 96 nvidia nemotron-3.5-lightning-30b-a3b 190 ms first token · 163 tok/s compare
- 95 nvidia nemotron-3.5-bolt-e4b 118 ms first token · 83.8 tok/s compare
- 94 nvidia nemotron-3-nano-omni-30b-a3b-reasoning 179 ms first token · 90.5 tok/s compare
- 93 nvidia nemotron-3.5-super-vl-120b-a12b 334 ms first token · 126 tok/s compare
- 90 poolside laguna-xs-2.1 171 ms first token · 31.0 tok/s compare
- 89 nvidia nemotron-3-ultra-550b-a55b 414 ms first token · 40.1 tok/s compare