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.

poolside

laguna-xs-2.1

Serving

Rank 3 of 16 Last probed (22 min ago)

poolside/laguna-xs-2.1 answered 100% of probes on the NVIDIA NIM free API in the last 30 days, with a median time to first token of 175 ms and 39.8 tok/s. It ranks 3 of 16 tracked models.

100% Uptime 15/15 probes
91/ 100 Score 0 round wins
175 ms First token p95 635 ms
4.87 s Full reply median
1.75 s Best reply fastest in range
39.8tok/s Throughput median

Model vs. median

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

Uptime
100% 77.3%
23 pts above median
First token
175 ms 16.6 s
95× better than median
Full reply
4.87 s 22.6 s
4.6× better than median
Throughput
39.8 tok/s 18.0 tok/s
2.2× better than median

laguna-xs-2.1 median of answering models

Error breakdown

0 failed of 15 probes, last 30 days.

No failed probes in this range.

Time to first token

Each probe. Lower is better.

0 ms250 ms500 ms750 ms1.00 s11-15 22:4411-17 16:13 UTC
answered no answer

Throughput

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

0.0 tok/s50.0 tok/s100 tok/s150 tok/s200 tok/s11-15 22:4411-17 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
OK157 ms10.5 s16.7 tok/s
OK136 ms4.87 s34.0 tok/s
OK178 ms5.59 s31.0 tok/s
OK181 ms9.88 s19.0 tok/s
OK196 ms6.01 s30.1 tok/s
OK133 ms9.01 s18.6 tok/s
OK171 ms3.08 s57.3 tok/s
OK195 ms7.49 s22.3 tok/s
OK148 ms2.07 s88.9 tok/s
OK635 ms4.91 s39.8 tok/s
OK184 ms2.21 s74.2 tok/s
OK156 ms2.64 s73.7 tok/s
OK244 ms1.85 s112 tok/s
OK175 ms2.11 s85.9 tok/s
OK142 ms1.75 s107 tok/s

Call laguna-xs-2.1

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": "poolside/laguna-xs-2.1",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256,
    "stream": true
  }'

Other models answering

Top of the leaderboard right now.