Coffee Vram

From its catalog listing
VRAM fit-check, call queue, keep-warm and idle eviction for local Ollama models, with a desktop status chip showing the active Hermes model (cloud or local), context, and tok/s, plus /vram. The panel includes a Performance pet and host stats (GPU, RAM, CPU, network).
Good to know before installing
when a local Ollama model won't fit, Coffee holds that call for up to the queue timeout (default 600 s) and, by default, unloads idle Ollama models (including ones other apps loaded, unless pinned) to make room; it also refreshes keep-alive on loaded models and polls the configured Ollama URL and NVIDIA telemetry in the background.
From its catalog listing.
How to install
- Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install coffee-vram - Said no? Turn it on later:
hermes plugins enable coffee-vram - Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide (opens in a new tab).
- Category
- Cost, speed & monitoring · AI models & providers
- Maintained by
- jimmy77733 (Community)
- Needs
- No API keys declared
- Adds tools
vram_status- Adds hooks
post_api_requestapi_request_error- Needs Hermes
- 0.22.0 or newer
- Version
- 0.1.4
- In the catalog
- 2026-11-09, updated 2026-11-11
Using the Hermes desktop app? See where plugins live

Full setup & settings ↗Source code ↗
More in cost, speed & monitoring
All cost, speed & monitoring plugins
New Hermes Agent updates every day on X. Follow @HermesWatcher