model
Llama 3.1 8B llm
A model record: onboarded once for the project and used by any eval's arms.
- weights
- open
- licence
- LLAMA 3.1 COMMUNITY LICENSE AGREEMENT
- aliases
llama3.1:8b- settings
- defaults
- onboarding
- onboarded, no arm smoked 2026-10-31
- best result per goal
- #2 of 55 Triage decisions on Orrery's error signals
01deployments and their onboarding
x3 · x3 · ollama 0.40.13 · llama3.1:8b · onboarding pass 2026-10-31 · 39.8 tokens/s
- where
- x3
- server or device
- ollama 0.40.13
- build
llama3.1:8b46e0c10c039e019119339687c3c1757cc81b9da49709a3b3924863ba87ca666eQ4_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 llama3.1:8b | — |
| digest found | 46e0c10c039e019119339687c3c1757cc81b9da49709a3b3924863ba87ca666e | — |
| default | s 4.67 · tokens out 19 · reasoned: no · finish stop | — |
| chosen | s 0.48 · tokens out 19 · reasoned: no · finish stop · settings () | — |
| tokens per s | 39.8 | — |
| deterministic | yes | — |
| json valid | yes | — |
dgx · dgx · ollama 0.40.13 · llama3.1:8b · onboarding pass 2026-10-31 · 41.5 tokens/s
- where
- dgx
- server or device
- ollama 0.40.13
- build
llama3.1:8b46e0c10c039e019119339687c3c1757cc81b9da49709a3b3924863ba87ca666e- 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 llama3.1:8b | — |
| digest found | 46e0c10c039e019119339687c3c1757cc81b9da49709a3b3924863ba87ca666e | — |
| default | s 4.68 · tokens out 22 · reasoned: no · finish stop | — |
| chosen | s 0.53 · tokens out 22 · reasoned: no · finish stop · settings () | — |
| tokens per s | 41.5 | — |
| deterministic | yes | — |
| json valid | yes | — |
mac · mac · ollama 0.40.13 · llama3.1:8b · onboarding pass 2026-10-31 · 34.5 tokens/s
- where
- mac
- server or device
- ollama 0.40.13
- build
llama3.1:8b46e0c10c039e019119339687c3c1757cc81b9da49709a3b3924863ba87ca666eQ4_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 llama3.1:8b | — |
| digest found | 46e0c10c039e019119339687c3c1757cc81b9da49709a3b3924863ba87ca666e | — |
| default | s 5.01 · tokens out 19 · reasoned: no · finish stop | — |
| chosen | s 0.55 · tokens out 19 · reasoned: no · finish stop · settings () | — |
| tokens per s | 34.5 | — |
| deterministic | yes | — |
| json valid | yes | — |
What it can do, across its deployments: reasons: no · json mode: yes
02settings history
No change of settings or build is recorded.
03arms
| arm | deployment | goal | its settings | arm smoke | result |
|---|---|---|---|---|---|
| triage_local_dgx_llama31_8b_v1 · rescored 5f2c057c orrery_triage_v1_labelled | dgx | Triage decisions on Orrery's error signals | call_timeout_s 600 | none | triage_cost 0.415 |
| triage_local_mac_llama31_8b_v1 · rescored 5f2c057c orrery_triage_v1_labelled | mac | Triage decisions on Orrery's error signals | call_timeout_s 600 | none | triage_cost 0.415 |
| triage_local_x3_llama31_8b_v1 · rescored 5f2c057c orrery_triage_v1_labelled | x3 | Triage decisions on Orrery's error signals | — | none | triage_cost 0.415 |