FitLLM
run.fitllm/fitllm · v1.0.0 · MCP 2025-11-25
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
Reachability
reachable
checked 2026-07-14 04:33 UTC
Registry status active
Tools pinned 3
7abea18b3245
Tools last changed
unchanged since first capture 2026-07-14
Provenance
Registry namespace run.fitllm
(domain verified by the official registry)
Repository
github.com/click6067-ship-it/fitllm-engine
Website
https://fitllm.run
Remote endpoints
https://fitllm.run/api/mcp (streamable-http)
Observed changes
| When (UTC) | Event | Detail |
|---|---|---|
| 2026-07-14 03:27 | first capture | 3 tools pinned |
Pinned tool definitions (3)
| Tool | Description |
|---|---|
| check_llm_fit | Check 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 full memory breakdown (weights, KV cache, overhead), max context, and a concrete fix if it... |
| what_fits_on_hardware | Rank which popular local LLMs fit on a given GPU or Apple Silicon Mac (at ~4-bit quantization, 8K context) — 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>?",... |
| list_supported | List the built-in model names and hardware names this fit-checker knows (for mapping user wording to exact names). Any public HuggingFace model also works via fitllm.run. |
Status badge
[](https://toolpin.dev/servers/run.fitllm/fitllm)
Maintain this server? Add the badge to your README — it links your users to this live status page.