{"slug": "kimi-k3-in-c-a-2-78t-parameter-model-no-gpu-8-gb-of-ram", "title": "Kimi-k3-in-C: A 2.78T-parameter model. No GPU. 8 GB of RAM", "summary": "A GitHub project by FareedKhan-dev, kimi-k3-in-c, runs inference on a 2.78-trillion-parameter Kimi K3 model on a single CPU using 8.24 GB of RAM, written in portable C99 with no BLAS, no framework and no GPU. The repository's headline claim is that a model of that scale can execute without GPU acceleration or a machine-learning framework.", "body_md": "GitHub - FareedKhan-dev/kimi-k3-in-c: A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. · GitHub\n\nYou signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert", "url": "https://wpnews.pro/news/kimi-k3-in-c-a-2-78t-parameter-model-no-gpu-8-gb-of-ram", "canonical_source": "https://github.com/FareedKhan-dev/kimi-k3-in-c", "published_at": "2026-11-03 19:55:00+00:00", "updated_at": "2026-11-03 20:20:44.213398+00:00", "lang": "en", "topics": ["large-language-models", "ai-infrastructure", "ai-tools", "machine-learning"], "entities": ["FareedKhan-dev", "Kimi K3", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/kimi-k3-in-c-a-2-78t-parameter-model-no-gpu-8-gb-of-ram", "markdown": "https://wpnews.pro/news/kimi-k3-in-c-a-2-78t-parameter-model-no-gpu-8-gb-of-ram.md", "text": "https://wpnews.pro/news/kimi-k3-in-c-a-2-78t-parameter-model-no-gpu-8-gb-of-ram.txt", "jsonld": "https://wpnews.pro/news/kimi-k3-in-c-a-2-78t-parameter-model-no-gpu-8-gb-of-ram.jsonld"}}