# FitLLM

**Canonical:** https://apis.io/providers/fitllm-run/  
**Website:** https://fitllm.run/  
**APIs profiled:** 1

FitLLM provides a free, auditable calculator that determines whether a local large language model (LLM) can fit within the VRAM of NVIDIA GPUs or the unified memory of Apple Silicon Macs. It accounts for model weights, quantization, KV‑cache size, attention types, and runtime overhead, offering accurate memory estimates for various architectures and configurations.

## Kin Score — 24.0 / 100 (emerging)

Scored 2026-11-13 under rubric 0.28.0.

| Facet | Score |
|---|---|
| Discoverability | 66.1 |
| Contract Quality | 34.3 |
| Contract Governance | 18.2 |
| Operational Transparency | 19.0 |
| Developer Ergonomics | 28.6 |
| Access Clarity | 0.0 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 4.5 (matched via fallback).

## Agent readiness — 15.5 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | derived |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |
| Pagination Ratio | na |
| Operation Distinctiveness | distinct |
| MCP Tool Quality | na |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## APIs (2)

- **FitLLM Agent API** — FitLLM provides a free calculator to determine if a local LLM fits within GPU VRAM or Apple Silicon memory.
- **FitLLM Agent API API** — Will this local LLM fit this hardware? Auditable, architecture-aware memory estimates (MLA / sliding-window / hybrid-linear / MoE), with documented runtime/OS reserves. No auth,...

## Security (1)

- **FitLLM Domain Security** — TLSv1.3 · HSTS

## Tags

Artificial Intelligence, LLM, Calculator, GPU, Memory

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/fitllm-run/). Scores are computed from the provider's own public artifacts under a published rubric.