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

llama-3.2-90b-vision-instruct

Unstable

Rank 9 of 15 Last probed (22 min ago)

meta/llama-3.2-90b-vision-instruct answered 74.7% of probes on the NVIDIA NIM free API in the last 7 days, with a median time to first token of 9.73 s and 4.8 tok/s. It ranks 9 of 15 tracked models.

74.7% Uptime 118/158 probes
56/ 100 Score 0 round wins
9.73 s First token p95 237.2 s
81.0 s Full reply median
38.2 s Best reply fastest in range
4.8tok/s Throughput median

Model vs. median

Against the median of models that answered, last 7 days.

Uptime
74.7% 74.7%
at the median
First token
9.73 s 14.8 s
1.5× better than median
Full reply
81.0 s 22.6 s
3.6× worse than median
Throughput
4.8 tok/s 22.3 tok/s
4.6× worse than median

llama-3.2-90b-vision-instruct median of answering models

Error breakdown

40 failed of 158 probes, last 7 days.

FailureProbesShare of failures
Not served (404)21 52.5%
Timed out14 35.0%
Empty answer4 10.0%
Server error (5xx)1 2.5%

Time to first token

Each probe. Lower is better.

0 ms125.0 s250.0 s375.0 s500.0 s11-10 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/s5.0 tok/s10.0 tok/s15.0 tok/s20.0 tok/s11-10 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
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a
Not served (404)n/an/an/a

Call llama-3.2-90b-vision-instruct

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/llama-3.2-90b-vision-instruct",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.