Skills Guide

MetriLLM - Find Best Local LLM for Your Hardware

VerifiedCaution

Tests speed, quality and RAM fit of local LLMs, then tells you if a model is worth running on your hardware.

Download and use
Sby Skills Guide Bot
Data & AIBeginner
7/27/2026
Claude CodeCursorCodex
#local-llm#benchmarking#ollama#lm-studio#performance-testing

Recommended for

Claude CodeCursorCodexData scientistData & analysis

Automated summary

MetriLLM benchmarks a local LLM on your machine and returns a verdict on how well it fits your hardware, measuring speed, quality and memory footprint.

Strengths

  • Produces a clear verdict (EXCELLENT down to NOT RECOMMENDED) instead of raw numbers alone
  • Combines performance metrics (tokens/s, TTFT, memory) with quality scoring across several task types
  • --perf-only mode for quick tests and --json output that scripts can consume
  • Works with Ollama or LM Studio, two common local runtimes

Limitations

  • Requires Node.js 20+, a global npm install and an already-running Ollama/LM Studio server
  • A full benchmark can take a while depending on model speed and response length
  • The --share flag uploads model, scores and hardware specs to a public leaderboard (no personal data, but worth knowing)
When to use it

When you need an objective answer on whether a local model runs fast and accurately enough on your own hardware before committing to it.

When not to use it

When you want to compare hosted API models or evaluate quality without running a benchmark on your local machine.

Security analysis

Caution
Quality score82/100

The skill does not contain destructive, exfiltrating, or obfuscated instructions. However, it asks the agent to globally install and execute an unpinned third-party npm CLI and optionally upload benchmark and hardware data to an external service, so it warrants caution rather than being fully safe.

Findings
  • •Installs and executes a third-party npm package globally with `npm install -g metrillm@latest`, which is unpinned and carries supply-chain risk.
  • •The optional `--share` flag uploads benchmark results and hardware specifications to a third-party service (`metrillm.dev`), though the skill states no personal data is sent.
  • •Uses Bash to run external CLI commands that interact with local model servers and write results under `~/.metrillm/results/`.
How this analysis is made

Examples

Full benchmark of a model
Benchmark llama3.2:3b with MetriLLM on this machine and tell me whether it's worth running day to day.
Quick speed check
Run a performance-only MetriLLM benchmark on qwen2.5-coder:7b and report tokens/s, time to first token and memory used.
Compare previous runs
List the results in ~/.metrillm/results/ and summarize which model got the best fitness verdict on this hardware.

name: metrillm description: 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. argument-hint: "[model-name]" author: MetriLLM source: https://github.com/MetriLLM/metrillm license: Apache-2.0 allowed-tools: Bash, Read install: npm install -g metrillm@latest

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

  1. Node.js 20+ — check with node -v
  2. Ollama or LM Studio installed and running
  3. MetriLLM CLI — install globally:
npm install -g metrillm@latest

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

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/download' --output '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md.part' && mv '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md.part' '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Bash, Read

Original excerpt: Prerequisites
  1. Node.js 20+ — check with node -v
  2. Ollama or LM Studio installed and running
  3. MetriLLM CLI — install globally:
npm install -g metrillm@latest

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md' && test -s '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/metrillm' && cp -R '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra' '.claude/skills/metrillm'

Cursor
test -f '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md' && test -s '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/metrillm' && cp -R '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra' '.cursor/skills/metrillm'

Codex
test -f '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md' && test -s '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/metrillm' && cp -R '.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra' '.agents/skills/metrillm'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra'

openskills read 'metrillm-find-best-local-llm-for-your-hardware-ms2s7bra'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/metrillm-find-best-local-llm-for-your-hardware-ms2s7bra/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Create Interactive Maps with kepler.gl

Data & AI

Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.

Claude CodeCursorCodexintermediateSafe 11,995
Skills Guide Bot

Agent-Driven Parameter Optimization

Data & AI

Guide for optimizing configurable systems with a measurable objective, using bounded trials and evidence-based recommendations.

Claude CodeCursorCodexintermediateSafe 45,609
Skills Guide Bot

ICP Visitor Outreach

Data & AI

Identify signed-up users matching the ideal customer profile but stalled, and draft personalized outreach to re-engage them.

Claude CodeintermediateSafe 6,843
Skills Guide Bot