IT Solutions Technology Blog

Ollama System One API – is based on TypeSafe’s Jev API and so you can send text and a set of questions to …/v1/systemone and it can be used to classify text answer yes/no questions or used to score text against a rubric

root@ra-ai-01:~# ollama version
Error: unknown command „version“ for „ollama“
root@ra-ai-01:~# ollama –version
ollama version is 0.33.2

root@ra-ai-01:~# curl -fsSL https://ollama.com/install.sh | sh
>>> Cleaning up old version at /usr/local/lib/ollama
>>> Installing ollama to /usr/local
>>> Downloading ollama-linux-amd64.tar.zst
################################### 100.0%
>>> Adding ollama user to render group…
>>> Adding ollama user to video group…
>>> Adding current user to ollama group…
>>> Creating ollama systemd service…
>>> Enabling and starting ollama service…
>>> NVIDIA GPU installed.
root@ra-ai-01:~# ollama –version
ollama version is 0.35.0

root@ra-ai-01:~#

Nimble is a 9B decision model from Bespoke Labs fine tuned from Qwen3.5-9B

You send Nimble some text and a set of questions it picks an answer for every question and gives you the probability of each allowed answer and Nimble reads the prompt once per question and scores the answer tokens directly

There’s no reasoning step this is what makes it fast

root@ra-ai-01:~# ollama pull nimble
pulling manifest
pulling bbf1d6fc03bb: 100% ▕██████████████████ ▏ 9.5 GB/9.5 GB 12 MB/s 0s
verifying sha256 digest
writing manifest
success

root@ra-ai-01:~#

root@ra-ai-01:~# ollama run nimble
>>> /bye

root@ra-ai-01:~#

root@ra-ai-01:~# curl http://localhost:11434/v1/systemone -d ‚{
„model“: „nimble“,
„state“: „Our checkout has returned 500 errors since 9am.“,
„questions“: {
„label“: {
„type“: „choice“,
„instructions“: „Which label fits this ticket?“,
„criteria“: {„billing“: null, „bug“: null, „account“: null}
}
}
}‘

Output

{
„model“: „nimble“,
„answers“: {
„team“: {
„type“: „choice“,
„choice“: „billing“,
„probabilities“: {„billing“: 0.984, „technical“: 0.011, „other“: 0.005},
„confidence“: 0.918
},
„refund“: {„type“: „noul“, „noul“: 0.997},
„urgency“: {
„type“: „score“,
„score“: 0.693,
„legend“: {„0“: „Routine“, „1“: „Soon“, „2“: „Urgent“},
„probabilities“: {„0“: 0.482, „1“: 0.342, „2“: 0.175},
„confidence“: 0.068
}
},
„usage“: {„input_tokens“: 841, „output_tokens“: 3}
}

root@ra-ai-01:~#