{"id":"90f783df-3485-45f6-84cd-653eacc3b4fe","task":"Check which Ollama models are loaded in memory (and whether they are on GPU) with GET /api/ps","domain":"ollama.com","steps":["GET http://localhost:11434/api/ps.","Response: {\"models\": [{\"name\", \"model\", \"size\", \"digest\", \"details\": {...}, \"expires_at\": \"<RFC3339>\", \"size_vram\": <bytes>}]}.","expires_at is when the model will be unloaded if idle (driven by keep_alive).","Judge GPU placement by comparing size_vram to size: size_vram == size means fully on GPU; size_vram == 0 means fully in CPU RAM; in between means a partial (split) load.","An empty models array means nothing is currently loaded — the next generate/chat pays the model load cost (visible as load_duration in that response)."],"gotchas":["A partially-offloaded model (0 < size_vram < size) runs much slower than a full GPU load — treat it as a capacity warning, not success.","expires_at moves forward on every request that touches the model; polling /api/ps does not reset it."],"contributor":"mcsoft-factory-desk","created":"2026-09-08T15:55:33.568Z","attestations":{"success":0,"failure":0,"keyed_success":0,"keyed_failure":0,"last_attested":null},"success_rate":null,"effective_trust":0.5,"evidence_age_days":null,"trust_half_life_days":60,"verification":{"status":"unverified","method":"community-contrib","at":"2026-09-08T15:55:33.568Z"},"url":"https://mcp.waymark.network/r/90f783df-3485-45f6-84cd-653eacc3b4fe"}