Skip to main content

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.

nvidia

nemotron-3.5-lightning-30b-a3b

Unstable

Rank 14 of 15 Last probed (22 min ago)

nvidia/nemotron-3.5-lightning-30b-a3b answered 6.5% of probes on the NVIDIA NIM free API in the last 14 days, with a median time to first token of 200 ms and 154 tok/s. It ranks 14 of 15 tracked models.

6.5% Uptime 21/325 probes
39/ 100 Score 14 round wins
200 ms First token p95 8.62 s
1.58 s Full reply median
758 ms Best reply fastest in range
154tok/s Throughput median

Model vs. median

Against the median of models that answered, last 14 days.

Uptime
6.5% 79.4%
73 pts below median
First token
200 ms 13.0 s
65× better than median
Full reply
1.58 s 22.6 s
14× better than median
Throughput
154 tok/s 21.3 tok/s
7.2× better than median

nemotron-3.5-lightning-30b-a3b median of answering models

Error breakdown

304 failed of 325 probes, last 14 days.

FailureProbesShare of failures
Empty answer303 99.7%
Timed out1 0.3%

Time to first token

Each probe. Lower is better.

0 ms12.5 s25.0 s37.5 s50.0 s11-03 17:0011-17 16:13 UTC
answered no answer

Throughput

Tokens per second after the first token, each probe. Higher is better.

0.0 tok/s125 tok/s250 tok/s375 tok/s500 tok/s11-03 17:0011-17 16:13 UTC
answered no answer

Availability heatmap

Last 7 days by UTC hour.

all answered some failed none answered not probed

Run history

Last 20 probes.

TimeResultFirst tokenFull replySpeed
OK163 ms1.38 s164 tok/s
OK173 ms4.98 s41.6 tok/s
OK205 ms1.36 s173 tok/s
OK190 ms1.41 s163 tok/s
OK305 ms1.60 s154 tok/s
OK187 ms1.22 s193 tok/s
OK251 ms1.37 s178 tok/s
OK224 ms1.58 s148 tok/s
OK200 ms2.38 s91.9 tok/s
OK167 ms1.34 s171 tok/s
OK157 ms1.74 s126 tok/s
OK197 ms1.13 s215 tok/s
Empty answern/an/an/a
Empty answern/an/an/a
OK196 ms1.34 s175 tok/s
Empty answern/an/an/a
Empty answern/an/an/a
Empty answern/an/an/a
Empty answern/an/an/a
Empty answern/an/an/a

Call nemotron-3.5-lightning-30b-a3b

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-3.5-lightning-30b-a3b",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.