ollama-bench 1.0.0 → 1.0.2

package/README.md

@@ -1,43 +1,61 @@
-# ollama-benchmark
+# Ollama Benchmark Script
+A command-line tool to benchmark and compare the performance of Ollama language models. Measures tokens per second, memory usage, and total processing time.
+
+## Setup
+
+### 1. Install Ollama
+Choose your platform:
+- **Windows:** [Download Installer](https://ollama.com/download/OllamaSetup.exe)
+- **macOS:** [Download App](https://ollama.com/download/Ollama-darwin.zip)
+- **Linux:** Run:
+  ```bash
+  curl -fsSL https://ollama.com/install.sh | sh
+  ```
+- **Docker:** Pull and run:
+  ```bash
+  docker pull ollama/ollama
+  docker run -d -v ollama:/root/.ollama -p 11434:11434 ollama/ollama
+  ```
+
+### 2. Start Ollama Server
+Before running any benchmarks, make sure the Ollama server is running:
 
-A command-line tool to benchmark Ollama models performance.
-
-## Prerequisites
-
-- Node.js >= 14.0.0
-- Ollama installed and running on your system
+```bash
+# On Linux/macOS terminal or Windows PowerShell
+ollama serve
+```
 
-## Installation
+For Windows users, you can also run Ollama from the system tray after installation.
 
-You can install globally:
+### 3. Install Benchmark Tool
+Install globally:
 ```bash
-npm install -g ollama-bench
+npm install -g ollama-benchmark
 ```
-
 Or run directly with npx:
 ```bash
-npx ollama-bench <model1> [model2] [model3] ...
+npx ollama-benchmark <model1> [model2] [model3]
 ```
 
 ## Usage
-
 ```bash
-ollama-bench mistral llama2 codellama
+# Using global installation
+ollama-benchmark smollm:135m qwen2.5:0.5b
+
+# Using npx (no installation required)
+npx ollama-benchmark smollm:135m qwen2.5:0.5b
 ```
 
-This will:
-1. Pull the specified models if not already present
-2. Run a benchmark test on each model
-3. Compare and display the results
-4. Show the best performing model
+## Troubleshooting
+
+If you encounter errors, check:
+1. Is the Ollama server running? (`ollama serve`)
+2. Can you access `http://localhost:11434`?
+3. Do you have enough RAM for your chosen models?
 
-## Output
+## Available Models
 
-The tool provides real-time feedback with:
-- Loading animations during operations
-- Color-coded status messages
-- Detailed benchmark results
-- Comparison of model performance
+See [ollama.com/library](https://ollama.com/library) for all available models.
 
 ## License
 

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "ollama-bench",
-    "version": "1.0.0",
+    "version": "1.0.2",
     "description": "A CLI tool to benchmark Ollama models performance",
     "main": "dist/index.js",
     "type": "module",
@@ -15,6 +15,14 @@
     "keywords": ["ollama", "benchmark", "ai", "models", "cli"],
     "author": "dalist1",
     "license": "MIT",
+    "repository": {
+        "type": "git",
+        "url": "git+https://github.com/dalist1/ollama-bench.git"
+    },
+    "bugs": {
+        "url": "https://github.com/dalist1/ollama-bench/issues"
+    },
+    "homepage": "https://github.com/dalist1/ollama-bench#readme",
     "dependencies": {
         "ollama": "latest"
     },