ollama-bench 1.0.1 → 1.0.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +18 -6
- package/package.json +9 -1
package/README.md
CHANGED
|
@@ -1,13 +1,10 @@
|
|
|
1
1
|
# Ollama Benchmark Script
|
|
2
|
-
|
|
3
2
|
A command-line tool to benchmark and compare the performance of Ollama language models. Measures tokens per second, memory usage, and total processing time.
|
|
4
3
|
|
|
5
4
|
## Setup
|
|
6
5
|
|
|
7
6
|
### 1. Install Ollama
|
|
8
|
-
|
|
9
7
|
Choose your platform:
|
|
10
|
-
|
|
11
8
|
- **Windows:** [Download Installer](https://ollama.com/download/OllamaSetup.exe)
|
|
12
9
|
- **macOS:** [Download App](https://ollama.com/download/Ollama-darwin.zip)
|
|
13
10
|
- **Linux:** Run:
|
|
@@ -20,20 +17,27 @@ Choose your platform:
|
|
|
20
17
|
docker run -d -v ollama:/root/.ollama -p 11434:11434 ollama/ollama
|
|
21
18
|
```
|
|
22
19
|
|
|
23
|
-
### 2.
|
|
20
|
+
### 2. Start Ollama Server
|
|
21
|
+
Before running any benchmarks, make sure the Ollama server is running:
|
|
22
|
+
|
|
23
|
+
```bash
|
|
24
|
+
# On Linux/macOS terminal or Windows PowerShell
|
|
25
|
+
ollama serve
|
|
26
|
+
```
|
|
24
27
|
|
|
28
|
+
For Windows users, you can also run Ollama from the system tray after installation.
|
|
29
|
+
|
|
30
|
+
### 3. Install Benchmark Tool
|
|
25
31
|
Install globally:
|
|
26
32
|
```bash
|
|
27
33
|
npm install -g ollama-benchmark
|
|
28
34
|
```
|
|
29
|
-
|
|
30
35
|
Or run directly with npx:
|
|
31
36
|
```bash
|
|
32
37
|
npx ollama-benchmark <model1> [model2] [model3]
|
|
33
38
|
```
|
|
34
39
|
|
|
35
40
|
## Usage
|
|
36
|
-
|
|
37
41
|
```bash
|
|
38
42
|
# Using global installation
|
|
39
43
|
ollama-benchmark smollm:135m qwen2.5:0.5b
|
|
@@ -42,6 +46,14 @@ ollama-benchmark smollm:135m qwen2.5:0.5b
|
|
|
42
46
|
npx ollama-benchmark smollm:135m qwen2.5:0.5b
|
|
43
47
|
```
|
|
44
48
|
|
|
49
|
+
## Troubleshooting
|
|
50
|
+
|
|
51
|
+
If you encounter errors, check:
|
|
52
|
+
1. Is the Ollama server running? (`ollama serve`)
|
|
53
|
+
2. Can you access `http://localhost:11434`?
|
|
54
|
+
3. Do you have enough RAM for your chosen models?
|
|
55
|
+
|
|
56
|
+
## Available Models
|
|
45
57
|
|
|
46
58
|
See [ollama.com/library](https://ollama.com/library) for all available models.
|
|
47
59
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "ollama-bench",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.2",
|
|
4
4
|
"description": "A CLI tool to benchmark Ollama models performance",
|
|
5
5
|
"main": "dist/index.js",
|
|
6
6
|
"type": "module",
|
|
@@ -15,6 +15,14 @@
|
|
|
15
15
|
"keywords": ["ollama", "benchmark", "ai", "models", "cli"],
|
|
16
16
|
"author": "dalist1",
|
|
17
17
|
"license": "MIT",
|
|
18
|
+
"repository": {
|
|
19
|
+
"type": "git",
|
|
20
|
+
"url": "git+https://github.com/dalist1/ollama-bench.git"
|
|
21
|
+
},
|
|
22
|
+
"bugs": {
|
|
23
|
+
"url": "https://github.com/dalist1/ollama-bench/issues"
|
|
24
|
+
},
|
|
25
|
+
"homepage": "https://github.com/dalist1/ollama-bench#readme",
|
|
18
26
|
"dependencies": {
|
|
19
27
|
"ollama": "latest"
|
|
20
28
|
},
|