FitLLM
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
Connect it
Settings → Connectors → Add custom connector
URL: https://fitllm.run/api/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://fitllm.run/api/mcp{
"mcpServers": {
"fitllm": {
"url": "https://fitllm.run/api/mcp"
}
}
}claude mcp add --transport http fitllm https://fitllm.run/api/mcp{
"servers": {
"fitllm": {
"type": "http",
"url": "https://fitllm.run/api/mcp"
}
}
}3 tools, verified live
check_llm_fitread-onlyCheck whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the memory breakdown (weights, KV cache, linear-attention state when present, runtime overhead, reserve), max context, and a concrete fix if it doesn't fit. Use this whenever a user asks anything like "can I run <model> on my <GPU/Mac>?", "will <model> fit in <N>G
what_fits_on_hardwareread-onlyRank which popular local LLMs fit on a given GPU or Apple Silicon Mac (at ~4-bit quantization, 8K context) â models that fit come first, biggest first, with max context each. Use when a user asks "what can I run on my <GPU/Mac/N GB>?", "best local model for my machine?", or gives hardware without naming a model.
list_supportedread-onlyList the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Standard text-only HuggingFace transformer configs can also be checked via fitllm.run; unsupported architectures are rejected.
Alternatives in AI & Agents
Compare →
SlopItB
Instant blogs for AI agents: sign up, publish markdown posts, get a live public URL in seconds.
OVOverwingB
Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
SASavvlyB
Savvly MCP: query fund data, model projections, and compare against alternative retirement products.
atomaB
Start and follow atoma builds; read their runs, traces, agent registry and skill catalogue.
TITickerDBB
Pre-computed market data that improves agent reasoning, reduces token usage, and replaces pipelines.
CAcnvs.appB
Real-time collaborative whiteboard — AI agents and humans edit the same board live over MCP.