{"slug": "llama-vim", "name": "llama.vim", "category": "editors", "category_name": "Editors and IDEs", "description": "", "recommenders": 4, "commenters": 4, "warners": 0, "score": 3.538, "rising": -1.31, "first": "2025-12-22", "latest": "2026-07-13", "why": "I use the vim equivalent, llama.vim [1] with Qwen3 Coder 30B and personally feel that it's better than Copilot.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 0, "compare": 0, "warn": 0}, "spark": [0, 1, 2, 0, 1, 0, 0, 0, 2, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I use the vim equivalent, llama.vim [1] with Qwen3 Coder 30B and personally feel that it's better than Copilot.", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/ggml-org/llama.vim", "official_url": "https://github.com/ggml-org/llama.vim", "pricing": "", "aliases": ["llama.vim"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 782282848, "item_id": 48892678, "url": "https://news.ycombinator.com/item?id=48892678", "by": "segmondy", "date": "2026-07-13", "version": null, "stance": "recommend", "quote": "https://github.com/ggml-org/llama.vim", "excerpt": "https://github.com/ggml-org/llama.vim", "context": "", "use_case": "AI completion in Vim", "switched_from": "", "story": "How do you use Vim in the era of AI?"}, {"id": 781925682, "item_id": 48870355, "url": "https://news.ycombinator.com/item?id=48870355", "by": "subulaz", "date": "2026-07-11", "version": null, "stance": "recommend", "quote": "there's also, e.g., this: https://voipnuggets.com/2025/03/30/supercharge-your-vim-editor-workflow-with-local-llms-introducing-llama-vim/", "excerpt": "i believe something like this: https://mwolson.org/blog/emacs/2025-12-03-my-emacs-ai-setup/ for those who use vim (me) there's also, e.g., this: https://voipnuggets.com/2025/03/30/supercharge-your-vim-editor-workflow-with-local-llms-introducing-llama-vim/", "context": "", "use_case": "local LLM completion in Vim", "switched_from": "", "story": "Companies are scrambling to curtail soaring AI costs"}, {"id": 758024864, "item_id": 47376554, "url": "https://news.ycombinator.com/item?id=47376554", "by": "segmondy", "date": "2026-03-14", "version": null, "stance": "recommend", "quote": "I use llama.vim - https://github.com/ggml-org/llama.vim", "excerpt": "I use llama.vim - https://github.com/ggml-org/llama.vim I run my own models, you can have models for code suggestion/FIM in the middle and you can have another for chat mode. You can point it to your local model if that's your thing or to a cloud model.", "context": "runs own models", "use_case": "local LLM code completion in Vim", "switched_from": "", "story": "Emacs and Vim in the Age of AI"}, {"id": 747494817, "item_id": 46718426, "url": "https://news.ycombinator.com/item?id=46718426", "by": "evanreichard", "date": "2026-01-22", "version": null, "stance": "recommend", "quote": "There's also https://github.com/ggml-org/llama.vim Which I've been using with Qwen3 Coder.", "excerpt": "There's also https://github.com/ggml-org/llama.vim Which I've been using with Qwen3 Coder. As long as infill is supported, that should work. I'll try later today.", "context": "", "use_case": "local code completion in Neovim", "switched_from": "", "story": "Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete"}, {"id": 747463696, "item_id": 46716481, "url": "https://news.ycombinator.com/item?id=46716481", "by": "dajonker", "date": "2026-01-22", "version": null, "stance": "recommend", "quote": "I use llama.vim with llama.cpp and the qwen2.5-coder 7B model.", "excerpt": "I use llama.vim with llama.cpp and the qwen2.5-coder 7B model. Easily fits on a 16 GB GPU and is fast even on a tiny RTX 2000 card with 70 watts of power. Quality of completions is good enough for me, if I want something more sophisticated I use something like Codex", "context": "", "use_case": "Neovim tab completion", "switched_from": "", "story": "Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete"}]}], "caveats": [], "who": [{"by": "segmondy", "context": "runs own models", "url": "https://news.ycombinator.com/item?id=47376554", "date": "2026-03-14"}], "tags": [], "use_cases": ["ai completion in vim", "local llm completion in vim", "local llm code completion in vim", "local code completion in neovim", "neovim tab completion", "local code completion"], "compared": [{"slug": "qwen", "name": "Qwen", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=46713106", "title": "Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48859439", "title": "How do you use Vim in the era of AI?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48870035", "title": "Companies are scrambling to curtail soaring AI costs", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47319071", "title": "Emacs and Vim in the Age of AI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46348329", "title": "A guide to local coding models", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"recommend": 1}, "2026-01": {"recommend": 2}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {"recommend": 2}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 782282848, "item_id": 48892678, "url": "https://news.ycombinator.com/item?id=48892678", "by": "segmondy", "date": "2026-07-13", "version": null, "stance": "recommend", "quote": "https://github.com/ggml-org/llama.vim", "excerpt": "https://github.com/ggml-org/llama.vim", "context": "", "use_case": "AI completion in Vim", "switched_from": "", "story": "How do you use Vim in the era of AI?"}, {"id": 781925682, "item_id": 48870355, "url": "https://news.ycombinator.com/item?id=48870355", "by": "subulaz", "date": "2026-07-11", "version": null, "stance": "recommend", "quote": "there's also, e.g., this: https://voipnuggets.com/2025/03/30/supercharge-your-vim-editor-workflow-with-local-llms-introducing-llama-vim/", "excerpt": "i believe something like this: https://mwolson.org/blog/emacs/2025-12-03-my-emacs-ai-setup/ for those who use vim (me) there's also, e.g., this: https://voipnuggets.com/2025/03/30/supercharge-your-vim-editor-workflow-with-local-llms-introducing-llama-vim/", "context": "", "use_case": "local LLM completion in Vim", "switched_from": "", "story": "Companies are scrambling to curtail soaring AI costs"}, {"id": 758024864, "item_id": 47376554, "url": "https://news.ycombinator.com/item?id=47376554", "by": "segmondy", "date": "2026-03-14", "version": null, "stance": "recommend", "quote": "I use llama.vim - https://github.com/ggml-org/llama.vim", "excerpt": "I use llama.vim - https://github.com/ggml-org/llama.vim I run my own models, you can have models for code suggestion/FIM in the middle and you can have another for chat mode. You can point it to your local model if that's your thing or to a cloud model.", "context": "runs own models", "use_case": "local LLM code completion in Vim", "switched_from": "", "story": "Emacs and Vim in the Age of AI"}, {"id": 747494817, "item_id": 46718426, "url": "https://news.ycombinator.com/item?id=46718426", "by": "evanreichard", "date": "2026-01-22", "version": null, "stance": "recommend", "quote": "There's also https://github.com/ggml-org/llama.vim Which I've been using with Qwen3 Coder.", "excerpt": "There's also https://github.com/ggml-org/llama.vim Which I've been using with Qwen3 Coder. As long as infill is supported, that should work. I'll try later today.", "context": "", "use_case": "local code completion in Neovim", "switched_from": "", "story": "Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete"}, {"id": 747463696, "item_id": 46716481, "url": "https://news.ycombinator.com/item?id=46716481", "by": "dajonker", "date": "2026-01-22", "version": null, "stance": "recommend", "quote": "I use llama.vim with llama.cpp and the qwen2.5-coder 7B model.", "excerpt": "I use llama.vim with llama.cpp and the qwen2.5-coder 7B model. Easily fits on a 16 GB GPU and is fast even on a tiny RTX 2000 card with 70 watts of power. Quality of completions is good enough for me, if I want something more sophisticated I use something like Codex", "context": "", "use_case": "Neovim tab completion", "switched_from": "", "story": "Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete"}, {"id": 741798944, "item_id": 46362434, "url": "https://news.ycombinator.com/item?id=46362434", "by": "evanreichard", "date": "2025-12-22", "version": null, "stance": "recommend", "quote": "I use the vim equivalent, llama.vim [1] with Qwen3 Coder 30B and personally feel that it's better than Copilot.", "excerpt": "Have you tried llama.vscode [0]? I use the vim equivalent, llama.vim [1] with Qwen3 Coder 30B and personally feel that it's better than Copilot. I have hot keys that allow me to quickly switch between the two and find myself always going back to local. [0] https://github.com/ggml-org/llama.vscode [1] https://github.com/ggml-org/llama.vim", "context": "", "use_case": "local code completion", "switched_from": "", "story": "A guide to local coding models"}]}