# MetriLLM

- **Website:** <https://metrillm.dev>
- **Primary alias:** `metrillm.dev`

## Description

MetriLLM is a leading platform for benchmarking local large language models (LLMs), designed to provide users with insights into performance tailored to their specific hardware needs. Known for its comprehensive Leaderboard, MetriLLM allows individuals and organizations to compare LLM efficiency across various setups, ensuring that users can identify the best configurations for their tasks. The platform showcases real benchmarks from an extensive range of hardware, with thousands of runs and dozens of unique models, empowering users to make informed decisions. MetriLLM facilitates community involvement by encouraging users to contribute their own benchmarks, enhancing the collective knowledge base. Whether you are utilizing Node.js, Ollama, or LM Studio, MetriLLM makes it easy to assess and optimize your local LLM performance. Keep up with the latest trends by receiving notifications on new hardware and model benchmarks, all while benefiting from an open-source community focused on advancing local machine learning capabilities. Discover the perfect LLM fit for your system with MetriLLM's data-driven approach.

## Industries

- 🖥 Computers Electronics and Technology
- 🖥 Artificial Intelligence and Machine Learning _(under Computers Electronics and Technology)_

## Links

- [twitter](https://twitter.com/MetriLLM)
- [github](https://github.com/MetriLLM)

## Logos & icons

- logo _(primary)_ — PNG — [download](https://cdn.brandfetch.io/idYi9k3zfE/w/180/h/180/theme/dark/logo.png?c=1bxid64Mup7aczewSAYMX&t=1788628264698)
- icon _(primary)_ — JPEG — [download](https://cdn.brandfetch.io/idYi9k3zfE/w/400/h/400/theme/dark/icon.jpeg?c=1bxid64Mup7aczewSAYMX&t=1788628265156)

## Colors

| Name | Hex | Theme |
| --- | --- | --- |
| Lightning Yellow | #f9b92a | accent |
| Ebony | #0a0e1a | dark |
| White | #fefefe | light |

## Fonts

- Chakra Petch — asset _(google)_
- ui-sans-serif — asset _(custom)_

## Imagery

- banner _(primary)_ — JPEG — [download](https://cdn.brandfetch.io/idYi9k3zfE/w/1500/h/500/iddV43M1Sb.jpeg?c=1bxid64Mup7aczewSAYMX&t=1788628264919)

---

_Source: <https://brandfetch.com/metrillm.dev>_
_See [/llms.txt](/llms.txt) for a full list of agent-readable pages, and [/auth.md](/auth.md) for how agents authenticate._