LarHope / ollama-benchmark
Ollama based Benchmark with detail I/O token per second. Python with Deepseek R1 example.
Why this job: says: benchmark; topics: benchmark
What it does
- Prompt processing speed. measures tokens/sec for input evaluation
- Generation speed. measures tokens/sec for output generation
- Model load time. tracks cold-start overhead
- Multi-model comparison. benchmark several models in a single run
- Table output. side-by-side comparison across models with -t
Get started
pip install git+https://github.com/LarHope/ollama-benchmark.git You need: Python 3.11 or higher; Ollama installed and running
- Maintenance
- Inactive
- Last commit 7 months ago
- Stars
- 174
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 50% closed
- 1 still open
- Pull requests
- 6 merged
- 4 waiting
- Releases
- None
- Never published
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| mlcommons / training | 1,778 | 16 days ago | Apache-2.0 | No downloads |
| TheAgentCompany / TheAgentCompany | 814 | 12 months ago | MIT | No downloads |
| TristanBilot / mlx-benchmark | 241 | 2 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- benchmark
- deepseek-r1
- llm
- ollama
- token
- tokenspeed
Project record
- JobEvals and observability
- StatusListed
- Commits20
- Forks16
- Watching1
- Stars in 28 days0
- CreatedFeb 16, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026