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-bolt-e4b

Serving

Rank 2 of 15 Last probed (9 min ago)

nvidia/nemotron-3.5-bolt-e4b answered 100% of probes on the NVIDIA NIM free API in the last 24 hours, with a median time to first token of 118 ms and 83.8 tok/s. It ranks 2 of 15 tracked models.

100% Uptime 12/12 probes
95/ 100 Score 1 round win
118 ms First token p95 262 ms
1.62 s Full reply median
1.46 s Best reply fastest in range
83.8tok/s Throughput median

Model vs. median

Against the median of models that answered, last 24 hours.

Uptime
100% 100%
at the median
First token
118 ms 414 ms
3.5× better than median
Full reply
1.62 s 4.91 s
3.0× better than median
Throughput
83.8 tok/s 31.0 tok/s
2.7× better than median

nemotron-3.5-bolt-e4b median of answering models

Error breakdown

0 failed of 12 probes, last 24 hours.

No failed probes in this range.

Time to first token

Each probe. Lower is better.

0 ms125 ms250 ms375 ms500 ms11-17 10:4311-17 16:13 UTC
answered no answer

Throughput

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

0.0 tok/s25.0 tok/s50.0 tok/s75.0 tok/s100 tok/s11-17 10:4311-17 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
OK146 ms1.82 s81.9 tok/s
OK146 ms1.88 s77.2 tok/s
OK91 ms1.62 s86.9 tok/s
OK130 ms1.59 s90.8 tok/s
OK110 ms1.70 s83.8 tok/s
OK102 ms1.55 s91.7 tok/s
OK178 ms1.89 s79.1 tok/s
OK262 ms9.61 s16.8 tok/s
OK139 ms1.75 s82.7 tok/s
OK118 ms1.46 s98.9 tok/s
OK111 ms1.57 s90.9 tok/s
OK87 ms1.54 s91.7 tok/s

Call nemotron-3.5-bolt-e4b

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-bolt-e4b",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.