About io.github.arose26/gguf-mcp
io.github.arose26/gguf-mcp is an MCP server in the Science category: inspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.
Install
claude mcp add io-github-arose26-gguf-mcp -- npx -y gguf-mcpnpx -y gguf-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (4)
estimate_vramFit check: exact weights size + modeled fp16 KV cache for your chosen context length
Parameters not published.
get_metadataThe GGUF key-value store (or safetensors `__metadata__`), filterable by key
Parameters not published.
inspect_modelOne-call summary: format, architecture, parameters, quantization, context length, file size, tensor count
Parameters not published.
list_tensorsTensor names, shapes, and storage types — filterable (`attn`, `blk.0`, ...)
Parameters not published.
Ask AI
Ask AI about io.github.arose26/gguf-mcp
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.