eval-harness

model

Llama 4 Scout llm

A model record: onboarded once for the project and used by any eval's arms.

weights
open
licence
LLAMA 4 COMMUNITY LICENSE AGREEMENT
aliases
llama4:scout
settings
defaults
onboarding
onboarded, no arm smoked 2026-10-31
best result per goal
#53 of 55 Triage decisions on Orrery's error signals

Every model

01deployments and their onboarding

x3 · x3 · ollama 0.40.13 · llama4:scout · onboarding pass 2026-10-31 · 15.7 tokens/s
where
x3
server or device
ollama 0.40.13
build
llama4:scout
bf31604e25c25d964e250bcf28a82bfbdbe88af5f236257fabb27629bb24c7f3
Q4_K_M
matches the record
yes
checked
2026-10-31
onboarded on
x3
probemeasurementflag
endpointprovider openai · base url http://127.0.0.1:11434/v1 · model llama4:scout—
digest foundbf31604e25c25d964e250bcf28a82bfbdbe88af5f236257fabb27629bb24c7f3—
defaults 24.96 · tokens out 22 · reasoned: no · finish stop—
chosens 1.4 · tokens out 22 · reasoned: no · finish stop · settings ()—
tokens per s15.7—
deterministicyes—
json validyes—
dgx · dgx · ollama 0.40.13 · llama4:scout · onboarding pass 2026-10-31 · 17.1 tokens/s
where
dgx
server or device
ollama 0.40.13
build
llama4:scout
bf31604e25c25d964e250bcf28a82bfbdbe88af5f236257fabb27629bb24c7f3
matches the record
yes
checked
2026-10-31
onboarded on
dgx
probemeasurementflag
endpointprovider openai · base url http://100.69.49.126:11434/v1 · model llama4:scout—
digest foundbf31604e25c25d964e250bcf28a82bfbdbe88af5f236257fabb27629bb24c7f3—
defaults 14.33 · tokens out 22 · reasoned: no · finish stop—
chosens 1.29 · tokens out 22 · reasoned: no · finish stop · settings ()—
tokens per s17.1—
deterministicyes—
json validyes—

What it can do, across its deployments: reasons: no · json mode: yes

02settings history

No change of settings or build is recorded.

03arms

armdeploymentgoalits settingsarm smokeresult
triage_local_dgx_llama4_scout_v1 · rescored 5f2c057c
orrery_triage_v1_labelled
dgxTriage decisions on Orrery's error signalscall_timeout_s 600nonetriage_cost 1.262