Report the selected GPU and server-wide Ollama model residency.

Includes device identity, source health/timestamps/coverage, claims, recent GPU activity, and pressure (ok|tight|degraded|thrashing|unknown). Unavailable residency is null; unavailable telemetry never establishes an empty or healthy GPU. Non-local memory pressure is a best-effort paging heuristic.

List the models currently resident in VRAM, with claim/busy detail.

Evict a single model from VRAM now (Ollama keep_alive=0).

Refuses by default if model has an active claim or a best-effort busy signal — pass force=True to override (busy is windowed and can lag a few seconds past a generation). by records who requested the eviction in the audit log (see history).

Free VRAM until at least gb GB is available. Skips claimed/busy models unless force=True. by records the requester in the audit log.

Also reports reserved_mb — how much of the resulting free VRAM other sessions have reserved for non-Ollama work (None if unreadable).

Load a model or refresh its keep-alive (e.g. "5m"; "-1" pins indefinitely).

An already resident model requires zero additional capacity. New loads account for reservations using an approximate model size; size_verified describes that estimate, while outcome describes verified residency. Returns succeeded|refused|failed|unknown. On unknown, inspect residency and pending_until before retrying. force=True bypasses admission checks but cannot override a pending operation. Zero durations must use unload().

Declare that you're using model for purpose.

Lets other sessions see who's using a model and why before deciding to evict it. Renew before ttl_seconds elapses if still in use — an un-renewed claim simply expires, so a crashed session never leaves a permanently-stuck claim.

Reserve gb GB of VRAM — a claim on capacity, not on a named model.

Use this for non-Ollama GPU work (a training run, a diffusion job) so other sessions can see the VRAM is spoken for. pid is advisory. Reservations expire by TTL like claims, so a crashed session never leaves one stuck.

COOPERATIVE: this gates vram-mcp's own warm(), but vram-mcp cannot intercept an Ollama auto-load triggered by a direct /api/generate call from another process.

Extend an existing claim's expiry before it lapses.

Release a claim early, before its TTL would expire.

See who's claiming what right now (all models, or one).

Suggest env/config changes to keep VRAM healthy (heuristics).

The VRAM audit trail, newest first: who ran unload/ensure_free/warm, and which models/processes appeared or disappeared (with a best-effort cause). Filter by model, type (action|disappeared|appeared), limit, or an ISO since floor. Answers 'what happened to model X?'.

Free-VRAM trend over the last hours, from the sampled audit log.

Answers "was this a gradual erosion or a sudden spike?" — the question a point-in-time vram_status() cannot. Returns direction, min/max/latest free MB (latest is null when the newest sample carries no reading), how many samples showed driver spill, and the raw samples.

samples holds at most the 200 most recent rows so a long window can't flood the caller's context; samples_truncated says whether older rows were dropped. Every summary figure is computed over the FULL window either way.