Skip to content
Model Lens

Quick Start

Get Model Lens running locally with a few commands.

Prerequisites

Section titled “Prerequisites”
  • Python 3.10+
  • A local LLM provider (we recommend LM Studio or Ollama)
  • At least one model loaded in your provider

Installation

Section titled “Installation”

  1. Clone the repository

    Terminal window
    git clone https://github.com/kevinjobin1/model-lens.git
    cd model-lens

  2. Install dependencies

    Terminal window
    pip install -r requirements.txt

  3. Install dev tooling (optional)

    Terminal window
    pip install ".[dev]"
    pre-commit install

  4. Verify installation

    Terminal window
    python apps/cli/modellens.py --help

Run your first benchmark

Section titled “Run your first benchmark”

If LM Studio is running with a model loaded:

Terminal window
python apps/cli/modellens.py run --quick

Model Lens auto-detects your provider and models.

Run a workload evaluation

Section titled “Run a workload evaluation”

Test models against real projects:

Terminal window
python apps/cli/modellens.py workload run --model qwen3.5-9b

Compare two models

Section titled “Compare two models”
Terminal window
python apps/cli/modellens.py run --framework compare --models qwen3.5 gemma-4

Start the dashboard

Section titled “Start the dashboard”
Terminal window
cd apps/dashboard
bun install
bun run dev          # → http://localhost:4321

Stream live events to the dashboard

Section titled “Stream live events to the dashboard”
9090/events
python apps/cli/modellens.py run --sse-port 9090

Next steps

Section titled “Next steps”