model
Nemotron 3.5 Lightning 30B llm
A model record: onboarded once for the project and used by any eval's arms.
- weights
- open
- licence
- NVIDIA Open Model License Agreement
- aliases
nemotron-3.5-lightning:30bnemotron-3.5-lightning:30b-a3b-q4_K_M- settings
reasoning_effortnone it reasoned by default on the onboarding probe (2026-10-31); off unless a task needs it (RUNBOOK §16): left at the server's default, one model reasons at length and the next not at all- onboarding
- vetted 2026-10-31
- best result per goal
- #21 of 55 Triage decisions on Orrery's error signals
01deployments and their onboarding
x3 · x3 · ollama 0.40.13 · nemotron-3.5-lightning:30b · onboarding pass 2026-10-31 · 61.6 tokens/s
- where
- x3
- server or device
- ollama 0.40.13
- build
nemotron-3.5-lightning:30be6905fffe2e2d9bbe325a9a2d2e074e3bd32683721bc6dfba409dede2f17f4dcQ4_K_M- matches the record
- yes
- checked
- 2026-10-31
- onboarded on
- x3
| probe | measurement | flag |
|---|---|---|
| endpoint | provider openai · base url http://127.0.0.1:11434/v1 · model nemotron-3.5-lightning:30b | — |
| digest found | e6905fffe2e2d9bbe325a9a2d2e074e3bd32683721bc6dfba409dede2f17f4dc | — |
| default | s 10.6 · tokens out 295 · reasoned: yes · finish stop | — |
| chosen | s 0.41 · tokens out 25 · reasoned: no · finish stop · settings (reasoning effort none) | — |
| tokens per s | 61.6 | — |
| deterministic | yes | — |
| json valid | yes | — |
dgx · dgx · ollama 0.40.13 · nemotron-3.5-lightning:30b · onboarding pass 2026-10-31 · 66.3 tokens/s
- where
- dgx
- server or device
- ollama 0.40.13
- build
nemotron-3.5-lightning:30be6905fffe2e2d9bbe325a9a2d2e074e3bd32683721bc6dfba409dede2f17f4dc- matches the record
- yes
- checked
- 2026-10-31
- onboarded on
- dgx
| probe | measurement | flag |
|---|---|---|
| endpoint | provider openai · base url http://100.69.49.126:11434/v1 · model nemotron-3.5-lightning:30b | — |
| digest found | e6905fffe2e2d9bbe325a9a2d2e074e3bd32683721bc6dfba409dede2f17f4dc | — |
| default | s 10.12 · tokens out 306 · reasoned: yes · finish stop | — |
| chosen | s 0.38 · tokens out 25 · reasoned: no · finish stop · settings (reasoning effort none) | — |
| tokens per s | 66.3 | — |
| deterministic | yes | — |
| json valid | yes | — |
mac · mac · ollama 0.40.13 · nemotron-3.5-lightning:30b-a3b-q4_K_M · onboarding pass 2026-10-31 · 44.9 tokens/s
- where
- mac
- server or device
- ollama 0.40.13
- build
nemotron-3.5-lightning:30b-a3b-q4_K_Me7a64ff15fb174c42b4f463e5c888c4f2c7b9cabf9e8d65a1c0874405426c1b2Q4_K_M- matches the record
- yes
- checked
- 2026-10-31
- onboarded on
- mac
| probe | measurement | flag |
|---|---|---|
| endpoint | provider openai · base url http://127.0.0.1:11435/v1 · model nemotron-3.5-lightning:30b-a3b-q4_K_M | — |
| digest found | e7a64ff15fb174c42b4f463e5c888c4f2c7b9cabf9e8d65a1c0874405426c1b2 | — |
| default | s 16.3 · tokens out 264 · reasoned: yes · finish stop | — |
| chosen | s 0.56 · tokens out 25 · reasoned: no · finish stop · settings (reasoning effort none) | — |
| tokens per s | 44.9 | — |
| deterministic | yes | — |
| json valid | yes | — |
What it can do, across its deployments: reasons: yes · json mode: yes · reasoning off reasoning_effort: none
02settings history
| when | what changed | why |
|---|---|---|
| 2026-10-31 | reasoning_effort: (server default) → none | it reasoned by default on the onboarding probe (2026-10-31); off unless a task needs it (RUNBOOK §16): left at the server's default, one model reasons at length and the next not at all |
03arms