176
total weekly downloads
2 packages
@nodegrove/llm-math
How much VRAM an open LLM needs and how fast it can run on a GPU: the memory, KV-cache and speed arithmetic behind nodegrove.io, with model data read from config.json and GPU specs from the makers.
@nodegrove/vram-mcp
MCP server: can this open LLM run on my GPU? VRAM, KV cache, speed ceilings and what would fit instead, with the exact math nodegrove.io uses. Any Hugging Face repo, any GPU.