model
Qwen 3.5 122B llm
A model record: onboarded once for the project and used by any eval's arms.
- weights
- open
- licence
- Apache-2.0
- aliases
qwen3.5:122beval-qwen35-122b- 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
- #45 of 55 Triage decisions on Orrery's error signals
01deployments and their onboarding
x3 · x3 · ollama 0.40.13 · qwen3.5:122b · onboarding pass 2026-10-31 · 14.7 tokens/s
- where
- x3
- server or device
- ollama 0.40.13
- build
qwen3.5:122b8b9d11d807c57feb1e2ecb0d6cbf40334c37dcc3523bed5540af4f927f112a37Q4_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 qwen3.5:122b | — |
| digest found | 8b9d11d807c57feb1e2ecb0d6cbf40334c37dcc3523bed5540af4f927f112a37 | — |
| default | s 65.96 · tokens out 537 · reasoned: yes · finish stop | — |
| chosen | s 1.84 · tokens out 27 · reasoned: no · finish stop · settings (reasoning effort none) | — |
| tokens per s | 14.7 | — |
| deterministic | yes | — |
| json valid | yes | — |
dgx · dgx · ollama 0.40.13 · qwen3.5:122b · onboarding pass 2026-10-31 · 18.9 tokens/s
- where
- dgx
- server or device
- ollama 0.40.13
- build
qwen3.5:122b8b9d11d807c57feb1e2ecb0d6cbf40334c37dcc3523bed5540af4f927f112a37- 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 qwen3.5:122b | — |
| digest found | 8b9d11d807c57feb1e2ecb0d6cbf40334c37dcc3523bed5540af4f927f112a37 | — |
| default | s 41.95 · tokens out 537 · reasoned: yes · finish stop | — |
| chosen | s 1.43 · tokens out 27 · reasoned: no · finish stop · settings (reasoning effort none) | — |
| tokens per s | 18.9 | — |
| deterministic | yes | — |
| json valid | yes | — |
hosted · homelab LiteLLM (the fleet's gateway) · eval-qwen35-122b · onboarding pass 2026-10-31 · 27.8 tokens/s · 2 accepted
- where
- homelab LiteLLM (the fleet's gateway)
- build
eval-qwen35-122b- matches the record
- yes
- checked
- 2026-10-31
- onboarded on
- homelab LiteLLM (the fleet's gateway)
| probe | measurement | flag |
|---|---|---|
| endpoint | provider litellm · base url http://homelab:4001/v1 · model eval-qwen35-122b | — |
| digest found | None | — |
| default | s 11.75 · tokens out 553 · reasoned: yes · finish stop | — |
| chosen | s 0.93 · tokens out 26 · reasoned: no · finish stop · settings (reasoning effort none) | — |
| tokens per s | 27.8 | — |
| deterministic | yes | — |
| json valid | yes | — |
Accepted: where it ran: a hosted gateway serves the provider's current build; there is no digest, revision or hash to pin; determinism: a hosted provider batches requests, so temperature 0 does not repeat exactly; repeats measure it
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
| arm | deployment | goal | its settings | arm smoke | result |
|---|---|---|---|---|---|
| triage_hosted_qwen35_122b_v1 · rescored 5f2c057c orrery_triage_v1_labelled | hosted | Triage decisions on Orrery's error signals | — | none | triage_cost 1.077 |
| triage_hosted_qwen35_122b_v2 · rescored 5f2c057c orrery_triage_v1_labelled | hosted | Triage decisions on Orrery's error signals | max_tokens 1024 | pass 2026-10-31 | triage_cost 0.877 |
| triage_local_dgx_qwen35_122b_v1 · rescored 5f2c057c orrery_triage_v1_labelled | dgx | Triage decisions on Orrery's error signals | — | none | triage_cost 1.138 |
| triage_local_dgx_qwen35_122b_v2 · rescored 5f2c057c orrery_triage_v1_labelled | dgx | Triage decisions on Orrery's error signals | max_tokens 1024, call_timeout_s 600 | pass 2026-10-31 | triage_cost 1.354 |