MarvinLabs vram_fit for Claude.ai
org.marvinlabs/vram-fit
Will a QLoRA fine-tune of gemma-3-4b-it fit your GPU? Verdicts from measured AMD and NVIDIA probes.
client:Claude.ai
transport:streamable-http
tools:3
Install MarvinLabs vram_fit in Claude.ai
Settings → Connectors → Add custom connector
https://marvinlabs.org/mcpClaude on the web takes a remote URL and completes OAuth in the browser. For a packaged server use Claude Desktop or Claude Code instead. Claude.ai docs