How do I install the Metrillm skill?

Run npx skillmds@latest add dvcrn/metrillm in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Metrillm safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Metrillm?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Metrillm free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Metrillm?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Metrillm by dvcrn — Agent Skill

Name: Metrillm
Rating: 4.2 (5 reviews)
Author: dvcrn

File contents

MetriLLM — Find the Best LLM for Your Hardware

Test any local model and get a clear verdict: is it worth running on your machine?

Prerequisites

Node.js 20+ — check with node -v
Ollama or LM Studio installed and running
- Ollama: ollama.com, then ollama serve
- LM Studio: lmstudio.ai, load a model and start the server
MetriLLM CLI — install globally:

npm install -g metrillm

Usage

List available models

ollama list

Run a full benchmark

metrillm bench --model $ARGUMENTS --json

This measures:

Performance: tokens/second, time to first token, memory usage
Quality: reasoning, math, coding, instruction following, structured output, multilingual
Fitness verdict: EXCELLENT / GOOD / MARGINAL / NOT RECOMMENDED

Performance-only benchmark (faster)

metrillm bench --model $ARGUMENTS --perf-only --json

Skips quality evaluation — measures speed and memory only.

View previous results

ls ~/.metrillm/results/

Read any JSON file to see full benchmark details.

Share to the public leaderboard

metrillm bench --model $ARGUMENTS --share

Uploads your result to the MetriLLM community leaderboard — an open, community-driven ranking of local LLM performance across real hardware. Compare your results with others and help the community find the best models for every setup. Shared data includes: model name, scores, hardware specs (CPU, RAM, GPU). No personal data is sent.

Interpreting Results

Verdict	Score	Meaning
EXCELLENT	>= 80	Fast and accurate — great fit
GOOD	>= 60	Solid — suitable for most tasks
MARGINAL	>= 40	Usable but with tradeoffs
NOT RECOMMENDED	< 40	Too slow or inaccurate

Key metrics to highlight:

tokensPerSecond > 30 = good for interactive use
ttft < 500ms = responsive
memoryUsedGB vs available RAM = will it fit?

Tips

Use --perf-only for quick tests
Close GPU-intensive apps before benchmarking
Benchmark duration varies depending on model speed and response length

Open Source

MetriLLM is free and open source (Apache 2.0). Contributions, issues, and feedback are welcome: github.com/MetriLLM/metrillm

---name: metrillmdescription: Find the best local LLM for your machine. Tests speed, quality and RAM fit, then tells you if a model is worth running on your hardware.---# MetriLLM — Find the Best LLM for Your HardwareTest any local model and get a clear verdict: is it worth running on your machine?## Prerequisites1. **Node.js 20+** — check with `node -v`2. **Ollama** or **LM Studio** installed and running - Ollama: [ollama.com](https://ollama.com), then `ollama serve` - LM Studio: [lmstudio.ai](https://lmstudio.ai), load a model and start the server3. **MetriLLM CLI** — install globally:```bashnpm install -g metrillm```## Usage### List available models```bashollama list```### Run a full benchmark```bashmetrillm bench --model $ARGUMENTS --json```This measures:- **Performance**: tokens/second, time to first token, memory usage- **Quality**: reasoning, math, coding, instruction following, structured output, multilingual- **Fitness verdict**: EXCELLENT / GOOD / MARGINAL / NOT RECOMMENDED### Performance-only benchmark (faster)```bashmetrillm bench --model $ARGUMENTS --perf-only --json```Skips quality evaluation — measures speed and memory only.### View previous results```bashls ~/.metrillm/results/```Read any JSON file to see full benchmark details.### Share to the public leaderboard```bashmetrillm bench --model $ARGUMENTS --share```Uploads your result to the [MetriLLM community leaderboard](https://metrillm.dev) — an open, community-driven ranking of local LLM performance across real hardware. Compare your results with others and help the community find the best models for every setup. Shared data includes: model name, scores, hardware specs (CPU, RAM, GPU). No personal data is sent.## Interpreting Results| Verdict | Score | Meaning ||---|---|---|| EXCELLENT | >= 80 | Fast and accurate — great fit || GOOD | >= 60 | Solid — suitable for most tasks || MARGINAL | >= 40 | Usable but with tradeoffs || NOT RECOMMENDED | < 40 | Too slow or inaccurate |Key metrics to highlight:- `tokensPerSecond` > 30 = good for interactive use- `ttft` < 500ms = responsive- `memoryUsedGB` vs available RAM = will it fit?## Tips- Use `--perf-only` for quick tests- Close GPU-intensive apps before benchmarking- Benchmark duration varies depending on model speed and response length## Open SourceMetriLLM is free and open source (Apache 2.0). Contributions, issues, and feedback are welcome: [github.com/MetriLLM/metrillm](https://github.com/MetriLLM/metrillm)

Frequently asked questions

Metrillm