run.fitllm/fitllm · v1.1.0 · ai-and-media
FitLLM is healthy: it completed an MCP handshake in 2095 ms and exposes 3 tools.
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
Endpoint: https://fitllm.run/api/mcp (streamable-http)
Repository · Website · JSON · Add to my inventory
| Users (last 30 days) | 0 |
| Handshake | Healthy |
| Auth needed | None |
| Tool count | 3 |
| Latency | 2095 ms |
| Last checked (UTC) | 2026-10-15T13:20:34.778Z |
| Checked (UTC) | Status | Latency | Error |
|---|---|---|---|
| 2026-10-15T13:20:34.778Z | Healthy | 2095 |
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 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 thi |
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>?", "best local model for my machine?", or gives hardware without na |
list_supported | List 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. |