{"slug": "llmfit", "name": "llmfit", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 8, "commenters": 14, "warners": 1, "score": 7.689, "rising": -1.29, "first": "2026-03-13", "latest": "2026-09-29", "why": "I recommend llmfit. It shows you exactly what models you can run and at what speeds", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 8, "neutral": 5, "compare": 0, "warn": 1}, "spark": [0, 0, 0, 0, 0, 4, 2, 0, 1, 0, 1, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I recommend llmfit. It shows you exactly what models you can run and at what speeds", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/alexsjones/llmfit", "official_url": "https://github.com/alexsjones/llmfit", "pricing": "", "aliases": ["llmfit", "LLMfit"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 798398960, "item_id": 49899935, "url": "https://news.ycombinator.com/item?id=49899935", "by": "capnjngl", "date": "2026-09-29", "stance": "recommend", "quote": "llmfit is your friend here", "excerpt": "I don't know about that specific use case, but llmfit is your friend here https://github.com/AlexsJones/llmfit", "context": "", "use_case": "Check local model fit", "switched_from": "", "story": "GLM-5.3 and the spread of advanced cyber capabilities"}, {"id": 783985552, "item_id": 48999097, "url": "https://news.ycombinator.com/item?id=48999097", "by": "efilife", "date": "2026-07-21", "stance": "recommend", "quote": "I recommend llmfit. It shows you exactly what models you can run and at what speeds", "excerpt": "I recommend llmfit. It shows you exactly what models you can run and at what speeds https://github.com/AlexsJones/llmfit", "context": "", "use_case": "checking which local LLMs fit hardware", "switched_from": "", "story": "I built a page that tells you what AI model your laptop can run"}, {"id": 770927056, "item_id": 48182941, "url": "https://news.ycombinator.com/item?id=48182941", "by": "kethinov", "date": "2026-05-18", "stance": "recommend", "quote": "I love the llmfit project for seeing what will run on your hardware", "excerpt": "Can someone explain what the current state of model benchmarking is? If you try to look up what the best locally runnable model is, you get a bunch of random blog posts using idiosyncratic criteria to rank things seemingly based on one dude's opinion. Ideally I would love to see a leaderboard with relatively objective ranking criteria that 1. lets you filter by open weight / locally runnable, 2. filter by date of rel", "context": "", "use_case": "checking which models fit hardware", "switched_from": "", "story": "Qwen 3.7 Preview"}, {"id": 770371744, "item_id": 48148234, "url": "https://news.ycombinator.com/item?id=48148234", "by": "karmakaze", "date": "2026-05-15", "stance": "recommend", "quote": "I wish they'd host on a free site", "excerpt": "This has a web version[0] which I wish they'd host on a free site. [0] https://github.com/AlexsJones/llmfit/tree/main/llmfit-web Edit: I tried to deploy a snapshot of the llmfit-web files on Netlify but it seems to need/want to talk to a backend[1] [1] https://llmfit.netlify.app/", "context": "", "use_case": "Local LLM hardware fit", "switched_from": "", "story": "Show HN: Find the best local LLM for your hardware, ranked by benchmarks"}, {"id": 765843008, "item_id": 47865188, "url": "https://news.ycombinator.com/item?id=47865188", "by": "chrsw", "date": "2026-04-22", "stance": "recommend", "quote": "These might help if the provider doesn't offer the same details themselves.", "excerpt": "These might help if the provider doesn't offer the same details themselves. Of course, we have to wait for the newly released models to get added to these sites. https://llmfit.io/ https://modelfit.io/", "context": "", "use_case": "estimating local model hardware fit", "switched_from": "", "story": "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 774379952, "item_id": 48398747, "url": "https://news.ycombinator.com/item?id=48398747", "by": "hypfer", "date": "2026-06-04", "stance": "warn", "quote": "After being annoyed by llmfit", "excerpt": "After being annoyed by llmfit, I've decided to become part of the problem and vibecode this. See also the GitHub repo readme: https://github.com/Hypfer/will-it-fit-llama-cpp I am probably very wrong in many ways, so now you have the opportunity to tell me exactly how in very colorful words :)", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Will It Fit? \u2013 Opinionated Normal People Llama.cpp VRAM Estimator"}]}], "who": [], "tags": [], "use_cases": ["check local model fit", "checking which local llms fit hardware", "checking which models fit hardware", "ranks local llms for hardware", "local llm hardware fit", "estimating local model hardware fit"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48146369", "title": "Show HN: Find the best local LLM for your hardware, ranked by benchmarks", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=47834565", "title": "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=47363754", "title": "Can I Run AI locally?", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49897075", "title": "GLM-5.3 and the spread of advanced cyber capabilities", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49346135", "title": "Show HN: Shoehorn \u2013 Quantize any model down to run on your machine", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48995134", "title": "I built a page that tells you what AI model your laptop can run", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"neutral": 2}, "2026-04": {"recommend": 4}, "2026-05": {"neutral": 2, "recommend": 2}, "2026-06": {"warn": 1}, "2026-07": {"recommend": 1}, "2026-08": {"neutral": 1}, "2026-09": {"recommend": 1}, "2026-10": {}}, "quotes": [{"id": 798398960, "item_id": 49899935, "url": "https://news.ycombinator.com/item?id=49899935", "by": "capnjngl", "date": "2026-09-29", "stance": "recommend", "quote": "llmfit is your friend here", "excerpt": "I don't know about that specific use case, but llmfit is your friend here https://github.com/AlexsJones/llmfit", "context": "", "use_case": "Check local model fit", "switched_from": "", "story": "GLM-5.3 and the spread of advanced cyber capabilities"}, {"id": 789560432, "item_id": 49347527, "url": "https://news.ycombinator.com/item?id=49347527", "by": "hmokiguess", "date": "2026-08-18", "stance": "neutral", "quote": "Reminds me of https://github.com/AlexsJones/llmfit", "excerpt": "Reminds me of https://github.com/AlexsJones/llmfit", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Shoehorn \u2013 Quantize any model down to run on your machine"}, {"id": 783985552, "item_id": 48999097, "url": "https://news.ycombinator.com/item?id=48999097", "by": "efilife", "date": "2026-07-21", "stance": "recommend", "quote": "I recommend llmfit. It shows you exactly what models you can run and at what speeds", "excerpt": "I recommend llmfit. It shows you exactly what models you can run and at what speeds https://github.com/AlexsJones/llmfit", "context": "", "use_case": "checking which local LLMs fit hardware", "switched_from": "", "story": "I built a page that tells you what AI model your laptop can run"}, {"id": 774379952, "item_id": 48398747, "url": "https://news.ycombinator.com/item?id=48398747", "by": "hypfer", "date": "2026-06-04", "stance": "warn", "quote": "After being annoyed by llmfit", "excerpt": "After being annoyed by llmfit, I've decided to become part of the problem and vibecode this. See also the GitHub repo readme: https://github.com/Hypfer/will-it-fit-llama-cpp I am probably very wrong in many ways, so now you have the opportunity to tell me exactly how in very colorful words :)", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Will It Fit? \u2013 Opinionated Normal People Llama.cpp VRAM Estimator"}, {"id": 770927056, "item_id": 48182941, "url": "https://news.ycombinator.com/item?id=48182941", "by": "kethinov", "date": "2026-05-18", "stance": "recommend", "quote": "I love the llmfit project for seeing what will run on your hardware", "excerpt": "Can someone explain what the current state of model benchmarking is? If you try to look up what the best locally runnable model is, you get a bunch of random blog posts using idiosyncratic criteria to rank things seemingly based on one dude's opinion. Ideally I would love to see a leaderboard with relatively objective ranking criteria that 1. lets you filter by open weight / locally runnable, 2. filter by date of rel", "context": "", "use_case": "checking which models fit hardware", "switched_from": "", "story": "Qwen 3.7 Preview"}, {"id": 770394689, "item_id": 48149668, "url": "https://news.ycombinator.com/item?id=48149668", "by": "desireco42", "date": "2026-05-15", "stance": "neutral", "quote": "selection was solid", "excerpt": "I got really good results when I asked Pi (agent) to install https://github.com/AlexsJones/llmfit and tell me which ones are good for me. It would organize it per use and selection was solid.", "context": "", "use_case": "ranks local LLMs for hardware", "switched_from": "", "story": "Show HN: Find the best local LLM for your hardware, ranked by benchmarks"}, {"id": 770371744, "item_id": 48148234, "url": "https://news.ycombinator.com/item?id=48148234", "by": "karmakaze", "date": "2026-05-15", "stance": "recommend", "quote": "I wish they'd host on a free site", "excerpt": "This has a web version[0] which I wish they'd host on a free site. [0] https://github.com/AlexsJones/llmfit/tree/main/llmfit-web Edit: I tried to deploy a snapshot of the llmfit-web files on Netlify but it seems to need/want to talk to a backend[1] [1] https://llmfit.netlify.app/", "context": "", "use_case": "Local LLM hardware fit", "switched_from": "", "story": "Show HN: Find the best local LLM for your hardware, ranked by benchmarks"}, {"id": 770352560, "item_id": 48147035, "url": "https://news.ycombinator.com/item?id=48147035", "by": "llagerlof", "date": "2026-05-15", "stance": "neutral", "quote": "What\u2019s new regarding llmfit?", "excerpt": "What\u2019s new regarding llmfit? https://github.com/AlexsJones/llmfit", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Find the best local LLM for your hardware, ranked by benchmarks"}, {"id": 765843008, "item_id": 47865188, "url": "https://news.ycombinator.com/item?id=47865188", "by": "chrsw", "date": "2026-04-22", "stance": "recommend", "quote": "These might help if the provider doesn't offer the same details themselves.", "excerpt": "These might help if the provider doesn't offer the same details themselves. Of course, we have to wait for the newly released models to get added to these sites. https://llmfit.io/ https://modelfit.io/", "context": "", "use_case": "estimating local model hardware fit", "switched_from": "", "story": "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"}, {"id": 765491168, "item_id": 47843198, "url": "https://news.ycombinator.com/item?id=47843198", "by": "greyskull", "date": "2026-04-20", "stance": "recommend", "quote": "", "excerpt": "It's certainly part of the problem. Thanks, I'll give that a shot.", "context": "", "use_case": "", "switched_from": "", "story": "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"}, {"id": 765487136, "item_id": 47842946, "url": "https://news.ycombinator.com/item?id=47842946", "by": "madtowneast", "date": "2026-04-20", "stance": "recommend", "quote": "You might want to try https://github.com/AlexsJones/llmfit", "excerpt": "You are experiencing the fact that you might not have enough VRAM to load the entire model at a time. You might want to try https://github.com/AlexsJones/llmfit", "context": "", "use_case": "checking model VRAM fit", "switched_from": "", "story": "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"}, {"id": 765424016, "item_id": 47839001, "url": "https://news.ycombinator.com/item?id=47839001", "by": "alx-ppv", "date": "2026-04-20", "stance": "recommend", "quote": "You can try https://github.com/AlexsJones/llmfit", "excerpt": "You can try https://github.com/AlexsJones/llmfit", "context": "", "use_case": "", "switched_from": "", "story": "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"}, {"id": 757884256, "item_id": 47367766, "url": "https://news.ycombinator.com/item?id=47367766", "by": "johnisgood", "date": "2026-03-13", "stance": "neutral", "quote": "Note: llmfit is not web-based.", "excerpt": "Why were you surprised? You can check out here how it does that: https://github.com/AlexsJones/llmfit/blob/main/llmfit-core/src/hardware.rs#L1318 To detect NVIDIA GPUs, for example: https://github.com/AlexsJones/llmfit/blob/main/llmfit-core/src/hardware.rs#L258 In this case it just runs the command \"nvidia-smi\". Note: llmfit is not web-based.", "context": "", "use_case": "checking hardware fit for local LLMs", "switched_from": "", "story": "Can I Run AI locally?"}, {"id": 757877776, "item_id": 47367361, "url": "https://news.ycombinator.com/item?id=47367361", "by": "dekhn", "date": "2026-03-13", "stance": "neutral", "quote": "it runs as native code", "excerpt": "We switched to talking about llmfit in this subthread, it runs as native code.", "context": "", "use_case": "run AI models locally", "switched_from": "", "story": "Can I Run AI locally?"}]}