Estimated game fps for any GPU or Apple Silicon chip, with the limiter and tweaks.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 3 tools
Each tool has a clear, non-overlapping purpose: check_game checks rig-game compatibility, compare compares hardware components, and recommend_upgrade suggests GPU upgrades. No ambiguity.
Two tools follow verb_noun pattern (check_game, recommend_upgrade), but 'compare' is just a verb, breaking the pattern slightly. Overall consistent and readable.
With 3 tools, the server is focused but covers the core workflows. While slightly low, it's appropriate for the domain of performance benchmarking and upgrade advice.
The tools cover checking compatibility, comparing hardware, and recommending upgrades. Minor gaps exist (e.g., no tool to view rig specs alone), but the main use cases are addressed.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_gamecomparerecommend_upgradeRead-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
Add one secure layer between your agents and this server.