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 10 of 16 Last probed (22 min ago)

meta/llama-3.2-90b-vision-instruct answered 78.0% of probes on the NVIDIA NIM free API in the last 30 days, with a median time to first token of 18.3 s and 4.4 tok/s. It ranks 10 of 16 tracked models.

78.0% Uptime 553/709 probes
56/ 100 Score 0 round wins
18.3 s First token p95 265.2 s
89.5 s Full reply median
31.9 s Best reply fastest in range
4.4tok/s Throughput median

Model vs. median

Against the median of models that answered, last 30 days.

Uptime
78.0% 77.3%
1 pts above median
First token
18.3 s 16.6 s
1.1× worse than median
Full reply
89.5 s 22.6 s
4.0× worse than median
Throughput
4.4 tok/s 18.0 tok/s
4.1× worse than median

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

Error breakdown

156 failed of 709 probes, last 30 days.

FailureProbesShare of failures
Timed out63 40.4%
Network error54 34.6%
Not served (404)21 13.5%
Empty answer17 10.9%
Server error (5xx)1 0.6%

Time to first token

Each probe. Lower is better.

0 ms125.0 s250.0 s375.0 s500.0 s10-31 14:0011-17 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/s10-31 14:0011-17 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.