{"slug": "ollama-confusion-about-model-size", "title": "Ollama: Confusion about model size", "summary": "A developer criticizes Ollama, a tool for running large language models locally, stating that its model size display ignores context and only accounts for weights, and recommends using llama.cpp directly instead due to Ollama's non-standard model hosting and patched version of llama.cpp with suboptimal flags.", "body_md": "Yes, it’s not taking the context into account, just the weights alone. You can check it out at huggingface:\n\nOther than that, I’d recommend against using ollama. It does not use huggingface directly and has its own weird model hosting, and it uses a version of llama.cpp with some weird patches of theirs and not optimal flags. If possible, I’d suggest you just to use llama.cpp directly.", "url": "https://wpnews.pro/news/ollama-confusion-about-model-size", "canonical_source": "https://forum.level1techs.com/t/ollama-confusion-about-model-size/254525#post_4", "published_at": "2026-08-28 16:23:18+00:00", "updated_at": "2026-08-28 16:51:08.368605+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models"], "entities": ["Ollama", "Hugging Face", "llama.cpp"], "alternates": {"html": "https://wpnews.pro/news/ollama-confusion-about-model-size", "markdown": "https://wpnews.pro/news/ollama-confusion-about-model-size.md", "text": "https://wpnews.pro/news/ollama-confusion-about-model-size.txt", "jsonld": "https://wpnews.pro/news/ollama-confusion-about-model-size.jsonld"}}