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.

meta

muse-glimmer-30b

Serving

Rank 9 of 15 Last probed (9 min ago)

meta/muse-glimmer-30b answered 91.7% of probes on the NVIDIA NIM free API in the last 24 hours, with a median time to first token of 33.4 s and 8.2 tok/s. It ranks 9 of 15 tracked models.

91.7% Uptime 11/12 probes
64/ 100 Score 0 round wins
33.4 s First token p95 133.1 s
61.1 s Full reply median
26.5 s Best reply fastest in range
8.2tok/s Throughput median

Model vs. median

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

Uptime
91.7% 100%
8 pts below median
First token
33.4 s 414 ms
81× worse than median
Full reply
61.1 s 4.91 s
12× worse than median
Throughput
8.2 tok/s 31.0 tok/s
3.8× worse than median

muse-glimmer-30b median of answering models

Error breakdown

1 failed of 12 probes, last 24 hours.

FailureProbesShare of failures
Timed out1 100%

Time to first token

Each probe. Lower is better.

0 ms50.0 s100.0 s150.0 s200.0 s11-17 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/s2.5 tok/s5.0 tok/s7.5 tok/s10.0 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
OK55.6 s91.2 s5.6 tok/s
OK41.2 s65.5 s8.2 tok/s
OK133.1 s167.6 s5.8 tok/s
OK10.3 s33.0 s8.8 tok/s
OK72.4 s96.9 s8.2 tok/s
OK26.4 s52.4 s7.7 tok/s
OK26.2 s47.8 s9.3 tok/s
Timed outn/an/an/a
OK33.4 s61.1 s7.2 tok/s
OK6.22 s30.4 s8.3 tok/s
OK3.35 s26.5 s8.6 tok/s
OK55.2 s88.0 s6.1 tok/s

Call muse-glimmer-30b

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": "meta/muse-glimmer-30b",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.