Localmaxxing
Localmaxxing provides community-sourced benchmarks for local LLM inference, allowing users to compare tokens per second, time-to-first-token, and VRAM usage across different GPUs, Apple Silicon, CPUs, and inference engines such as llama.cpp, Ollama, and LM Studio. It features a leaderboard of real hardware runs, model and hardware catalogs, quality evaluations, and a marketplace for buying/selling benchmarked hardware. The platform includes a CLI tool for submitting new benchmark results directly from users' own setups.
FreemiumMITWebCLI
21stars
2forks
6features
2026since
Overview
6 featuresLocalmaxxing sits in PulseGate's AI & ML category. It focuses on finding reliable, community-validated performance data for running LLMs locally on specific hardware configurations. It is built as a consumer product for AI developers and enthusiasts. There is a free tier. Localmaxxing is available on the web and the command line.
Localmaxxing first shipped in 2026. Development happens publicly on GitHub with 21 stars and 62 commits in the last 90 days. Key capabilities include leaderboard, Hardware Comparison, and Model Benchmarks. The interface is available in 17 languages, including German, English, and Spanish. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
- Leaderboard
- Hardware Comparison
- Model Benchmarks
- Community Evals
- CLI Tool
- Marketplace
Tags
local-llm-benchmarksinference-speedhardware-leaderboardllm-evals
AI capabilities
Text
Inference: Local
Built with & integrations
Framework
Next.js
Hosting
Cloudflare
AI providers
local_oss
Connectors
API
Runs on
BrowserCLI
Detected from
- Next.js
- x-powered-by header · /_next/static/ in the HTML · __next_f in the HTML
- local_oss
- bollama in the HTML · bllama in the HTML · bvllm in the HTML
- Cloudflare
- cf-ray header · cf-cache-status header
Trust & compliance
License
MIT
Verified signals
Indexing history
1What PulseGate has recorded for this listing
- Indexed23 Jul · 00:53 UTCLocalmaxxing – Local LLM Inference Benchmarks verified against its public sourceSource: PulseGate · Open
Frequently asked questions about Localmaxxing
- What is Localmaxxing?
- Localmaxxing focuses on finding reliable, community-validated performance data for running LLMs locally on specific hardware configurations. It is catalogued under AI & ML on PulseGate.
- Who should use Localmaxxing?
- Localmaxxing is a consumer product built for AI developers and enthusiasts.
- Does Localmaxxing have a free plan?
- Yes — there is a free tier, with paid plans for advanced use.
- What platforms does Localmaxxing run on?
- Localmaxxing runs on the web and the command line.
- Is Localmaxxing still maintained?
- The GitHub repository shows 62 commits in the last 90 days.
- What projects are similar to Localmaxxing?
- Similar projects tracked by PulseGate include BenchLoop, llm-speed, and inferbench-cli.BenchLoopllm-speedinferbench-cli
- How long has Localmaxxing been around?
- Localmaxxing first shipped in 2026.
- Is Localmaxxing open source?
- Localmaxxing has a public GitHub repository.
Similar apps
Closest matches by what these projects do