signerless/llm-checker

Advanced CLI tool that scans your hardware and tells you exactly which LLM or sLLM models you can run locally, with full Ollama integration.

What it solves

Choosing the right local LLM is difficult because of the vast number of model variants, quantization levels, and varying hardware constraints (VRAM, memory bandwidth). LLM Checker automates this by analyzing a user's specific hardware and recommending the best-fitting models from multiple registries.

How it works

The tool uses a hardware detection system to identify CPU, GPU (NVIDIA, AMD, Apple Silicon, Intel Arc), and RAM capabilities. It then applies a deterministic scoring engine across four dimensions—Quality, Speed, Fit, and Context—to rank models. It leverages a multi-source registry containing over 33,000 artifacts from Hugging Face, Ollama, and GPT4All, as well as a synced SQLite catalog of Ollama models. It also includes a structural safety validator (via ModelVet) to check GGUF and safetensors files before they are loaded.

Who it’s for

Developers and AI enthusiasts running local LLMs (specifically via Ollama) who want to find the most performant model for their specific machine without manual trial and error.

Highlights

  • Hardware-Aware Recommendations: Automatically detects system specs to suggest models that actually fit in memory.
  • Lage Model Registry: Access to 33k+ artifacts across Hugging Face, Ollama, and GPT4All.
  • MCP Server Integration: Built-in Model Context Protocol server allowing AI assistants like Claude or Cursor to manage local models and analyze hardware.
  • Safety Verification: Integrated structural validation for model files to prevent loading corrupted or malicious blobs.
  • Performance Metrics: ai-run command provides live tokens-per-second metrics during model execution.

Related

  • Project
    AlexsJones/llmfit

    A hardware-aware recommendation tool that analyzes your system specs to find the best-fitting open-source LLMs across various quantizations.

  • Project
    midudev/canirun.ai

    A hardware detection and recommendation tool that tells users which open-weight AI models will run best on their specific machine based on their CPU, RAM, and GPU.

  • Project
    Andyyyy64/whichllm

    whichllm is a CLI that detects your hardware (or a simulated GPU) and ranks Hugging Face LLMs that will actually run locally, using live benchmark data, memory‑fit estimates and speed predictions. It can output tables, Markdown, JSON, start a chat, or generate Python snippets, and includes planning commands for hardware upgrades.

  • Dispatch
    Optimizing Local LLM Selection: An In-Depth Look at whichllm

    Explore how whichllm solves the challenge of finding the best-performing local LLM for specific hardware using evidence-based ranking and VRAM estimation.

  • Project
    aidatatools/ollama-benchmark

    A CLI tool that benchmarks the token‑per‑second throughput of locally‑run Ollama models, automatically selecting models based on available RAM and reporting performance.