{"slug": "localmaxxing-local-llm-inference-benchmarks", "title": "Localmaxxing – Local LLM Inference Benchmarks", "summary": "LocalMaxxing, a community-driven platform for local large language model inference benchmarks, allows users to submit real hardware performance data via CLI or web form. Results appear immediately on public leaderboards, tracking tokens per second, time-to-first-token, and VRAM usage to compare models, hardware, and engines.", "body_md": "### Sign in & create a key\n\nSign in with GitHub, then create an API key in your dashboard so the CLI and your agents can submit runs.\n\nLocalMaxxing\n\nCommunity benchmarks for local LLM inference. Track speed, compare hardware, and find your optimal setup.\n\nEvery number on this site comes from a community-submitted run on real hardware — no vendor benchmarks.\n\nSign in with GitHub, then create an API key in your dashboard so the CLI and your agents can submit runs.\n\nMeasure tokens/sec, time-to-first-token and VRAM usage with the CLI, or submit results through the web form.\n\nResults appear on the public leaderboards immediately — compare models, hardware and engines to find your optimal setup.", "url": "https://wpnews.pro/news/localmaxxing-local-llm-inference-benchmarks", "canonical_source": "https://www.localmaxxing.com/en", "published_at": "2026-07-23 00:41:00+00:00", "updated_at": "2026-07-23 00:52:09.227793+00:00", "lang": "en", "topics": ["large-language-models", "ai-infrastructure", "developer-tools"], "entities": ["LocalMaxxing"], "alternates": {"html": "https://wpnews.pro/news/localmaxxing-local-llm-inference-benchmarks", "markdown": "https://wpnews.pro/news/localmaxxing-local-llm-inference-benchmarks.md", "text": "https://wpnews.pro/news/localmaxxing-local-llm-inference-benchmarks.txt", "jsonld": "https://wpnews.pro/news/localmaxxing-local-llm-inference-benchmarks.jsonld"}}