run.fitllm/fitllm
FitLLM
run.fitllm/fitllm costs 870 tokens of context per session. It has 3 tool definitions. That is 0.4 % of a 200k window. Measured 2026-10-03.
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
alive probed 2026-10-03 · HTTP 200
3tools
870tokens for the tool definitions
0.4 %of a 200k context window
1.3 sto initialize
131 msto list tools
- Endpoint
- https://fitllm.run/api/mcp (streamable-http)
- Host
- fitllm.run
- Protocol
- 2025-11-25
- Reports itself as
- fitllm 1.1.0
- Capabilities
- resources, tools
- Instructions
- none
- Repository
- https://github.com/click6067-ship-it/fitllm-engine
- Website
- https://fitllm.run
- Registry
- active, updated 2026-09-02 · registry entry
- Reachable
- 2 of the last 2 probes
Most expensive tools
| Tool | Tokens | Share of this server |
|---|---|---|
| check_llm_fit | 556 | 64 % |
| what_fits_on_hardware | 234 | 27 % |
| list_supported | 80 | 9 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Tokens |
|---|---|---|---|---|
| 2026-10-03 20:43 | alive | 1.3 s | 3 | 870 |
| 2026-10-03 17:57 | alive | 1.2 s | 3 | 870 |
Badge
[](https://mcp-pulse.ulehla.dev/s/run.fitllm/fitllm)