Skip to content
External endpointresponds

FitLLM

Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.

Endpoint URL
https://fitllm.run/api/mcp
Current status
responds
Last checked
Aug 17, 2026, 05:01 AM UTC
Check
MCP initialize · 8s limit
Latency
255 ms
Response record
4 of 4 rounds
Transport
streamable-http
Source
mcp_registry
Registry name
run.fitllm/fitllm

Current observation

This endpoint answered at its latest recorded check.

What this server reports about itself

Self-reported at initialize. Not verified by Licium.

Server name
fitllm
Version
1.1.0
Capability keys
tools, resources
Tool names
check_llm_fit, what_fits_on_hardware, list_supported

Reported Aug 17, 2026, 05:01 AM UTC.

Check history

Oldest to newest. Each row is one recorded check.

  1. responds
    MCP initialize · 8s limit · HTTP 200 · 615ms
  2. responds
    MCP initialize · 8s limit · HTTP 200 · 501ms
  3. responds
    MCP initialize · 8s limit · HTTP 200 · 244ms
  4. responds
    MCP initialize · 8s limit · HTTP 200 · 255ms