Claim 6 — Ollama dossier

CLAIM 6 / Ollama

Default context length based on VRAM — "< 24 GiB VRAM: 4k context, 24-48 GiB VRAM: 32k context, >= 48 GiB VRAM: 256k context"; agent and coding tasks "should be set to at least 64000 tokens"

as labeled

Observed

As documented — source-confirmed at HEAD 2026-06-11: envconfig/config.go defines OLLAMA_CONTEXT_LENGTH defaulting to 0 with VRAM-based resolution described as "4k/32k/256k based on VRAM"; release-verified that v0.15.5 (2026-02-03) introduced the tiers, superseding the historical flat 2,048-then-4,096 defaults (v0.6.7, 2025-04-26). The label is now accurate; the residual gap — the <24 GiB default sits below the vendor's own agent guidance, silently — is tracked as OL-01.

UPDATE 2026-06-28: v0.30.9 added an explicit error when a single message exceeds the context window — first progress on OL-01's silent-truncation criterion — but gradual multi-turn accumulation truncation remains silent.
UPDATE 2026-07-17(re-verified on v0.32.1): no further change to VRAM-tiered context defaults or truncation behavior in v0.31.1/v0.31.2/v0.32.0/v0.32.1 release notes; OL-01 remains open.

Evidence

[1][2][3]

Verification

verified 2026-07-20 · by probe-ci · probe probes/ollama/claim-6/