{"slug": "nemotron", "name": "Nemotron", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 7, "warners": 2, "score": 1.468, "rising": 0.35, "first": "2026-06-11", "latest": "2026-10-30", "why": "Olmo and to a lesser extent Nemotron are what you should look at", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 2, "compare": 0, "warn": 2}, "spark": [0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Olmo and to a lesser extent Nemotron are what you should look at", "icon": true, "domain": null, "github_repo": "github.com/nvidia-nemo/nemotron", "official_url": "https://github.com/nvidia-nemo/nemotron", "pricing": "", "aliases": ["Nemotron"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 787288390, "item_id": 49205524, "url": "https://news.ycombinator.com/item?id=49205524", "by": "alasr", "date": "2026-08-06", "stance": "recommend", "quote": "start with Qwen3.6, Google's Gemma4, OpenAI's gpt-oss-20b or Nvidia's Nemotron", "excerpt": "- See \"Llama.cpp vs Ollama\"[0] and \"Llama.cpp vs LM Studio\"[1] for a high-level features comparison and find out which one suite you best (check out the \"Target Users\" category[0][1], at least). - If you're still not sure, \"LM Studio\"[2] is not bad to start with as you'll be able to download, start/stop/manage and chat with your LLM model all in one place: a single desktop app. Also, once installed, enable \"Developer", "context": "", "use_case": "local LLM", "switched_from": "", "story": "Qwen3.8-Max: A New Bar for Coding and Cowork"}, {"id": 783431009, "item_id": 48964438, "url": "https://news.ycombinator.com/item?id=48964438", "by": "shade", "date": "2026-07-18", "stance": "recommend", "quote": "it works well", "excerpt": "Nice - I'm definitely going to take a look at this. I've built my own cross-platform (Mac/Win/Linux) live captioning app on top of Nemotron, and it works well but dealing with ONNX is kind of annoying. With this having Rust support (I built it on Rust/Tauri) it should be a pretty solid candidate; I'll have to see if I can find a Silero VAD implementation that doesn't depend on ONNX, or maybe I'll see if the clankers ", "context": "built a cross-platform live captioning app", "use_case": "live captioning app", "switched_from": "", "story": "Transcribe.cpp"}, {"id": 775862721, "item_id": 48491420, "url": "https://news.ycombinator.com/item?id=48491420", "by": "aesthesia", "date": "2026-06-11", "stance": "recommend", "quote": "Olmo and to a lesser extent Nemotron are what you should look at", "excerpt": "If you really want to see fully open training pipelines for modern LLMs, Olmo and to a lesser extent Nemotron are what you should look at. https://github.com/allenai/OLMo https://github.com/NVIDIA-NeMo/Nemotron", "context": "", "use_case": "fully open LLM training pipelines", "switched_from": "", "story": "Open Reproduction of DeepSeek-R1"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 801801472, "item_id": 50112592, "url": "https://news.ycombinator.com/item?id=50112592", "by": "enjoyyourlife", "date": "2026-10-16", "stance": "warn", "quote": "It's only good because it's free.", "excerpt": "It's only good because it's free. I love using it free on Nvidia platform and OpenRouter but otherwise Nemotron hasn't been good so far. It's nice that they are still working on it but this would have to be a major improvement to justify paying for it", "context": "", "use_case": "free LLM use", "switched_from": "", "story": "Nvidia Nemotron 3.5 Bolt 74B-A9B"}, {"id": 777986000, "item_id": 48624125, "url": "https://news.ycombinator.com/item?id=48624125", "by": "vcryan", "date": "2026-06-21", "stance": "warn", "quote": "Yesterday I used the latest one on OpenRouter and it was bad - worse than StepFun", "excerpt": "Maybe I'll give Nemotron another try. Yesterday I used the latest one on OpenRouter and it was bad - worse than StepFun", "context": "", "use_case": "trying model via OpenRouter", "switched_from": "", "story": "Apertus \u2013 Open Foundation Model for Sovereign AI"}]}], "who": [{"by": "shade", "context": "built a cross-platform live captioning app", "url": "https://news.ycombinator.com/item?id=48964438", "date": "2026-07-18"}], "tags": [], "use_cases": ["local llm", "cloud vision model", "free llm use", "live captioning app", "trying model via openrouter", "fully open llm training pipelines"], "compared": [{"slug": "gemma", "name": "Gemma", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=50309386", "title": "Show HN: Cerebellum \u2013 small model on the robot, big model for what it can't undo", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50110169", "title": "Nvidia Nemotron 3.5 Bolt 74B-A9B", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49150470", "title": "Qwen3.8-Max: A New Bar for Coding and Cowork", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48971128", "title": "Nvidia DGX Spark as a daily driver", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48963879", "title": "Transcribe.cpp", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48622778", "title": "Apertus \u2013 Open Foundation Model for Sovereign AI", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {"recommend": 1, "warn": 1}, "2026-07": {"recommend": 1, "neutral": 1}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {"warn": 1, "neutral": 1}}, "quotes": [{"id": 804955250, "item_id": 50309703, "url": "https://news.ycombinator.com/item?id=50309703", "by": "dminglv", "date": "2026-10-30", "stance": "neutral", "quote": "We used Nemotron on the Nebius Token Factory.", "excerpt": "This was built as part of the Nebius x NVIDIA hackathon. This is a piece of middleware to allow interaction between lightweight models on the robot and large vision language models on the cloud. In our example, we had a raspberry pi based sorting system. When a Kiwi was placed on the platform, our detection model (YOLOX-Nano) didn't recognise it (COCO classes). It therefore wanted to discard it. But because this acti", "context": "", "use_case": "cloud vision model", "switched_from": "", "story": "Show HN: Cerebellum \u2013 small model on the robot, big model for what it can't undo"}, {"id": 801801472, "item_id": 50112592, "url": "https://news.ycombinator.com/item?id=50112592", "by": "enjoyyourlife", "date": "2026-10-16", "stance": "warn", "quote": "It's only good because it's free.", "excerpt": "It's only good because it's free. I love using it free on Nvidia platform and OpenRouter but otherwise Nemotron hasn't been good so far. It's nice that they are still working on it but this would have to be a major improvement to justify paying for it", "context": "", "use_case": "free LLM use", "switched_from": "", "story": "Nvidia Nemotron 3.5 Bolt 74B-A9B"}, {"id": 787288390, "item_id": 49205524, "url": "https://news.ycombinator.com/item?id=49205524", "by": "alasr", "date": "2026-08-06", "stance": "recommend", "quote": "start with Qwen3.6, Google's Gemma4, OpenAI's gpt-oss-20b or Nvidia's Nemotron", "excerpt": "- See \"Llama.cpp vs Ollama\"[0] and \"Llama.cpp vs LM Studio\"[1] for a high-level features comparison and find out which one suite you best (check out the \"Target Users\" category[0][1], at least). - If you're still not sure, \"LM Studio\"[2] is not bad to start with as you'll be able to download, start/stop/manage and chat with your LLM model all in one place: a single desktop app. Also, once installed, enable \"Developer", "context": "", "use_case": "local LLM", "switched_from": "", "story": "Qwen3.8-Max: A New Bar for Coding and Cowork"}, {"id": 784234754, "item_id": 49014672, "url": "https://news.ycombinator.com/item?id=49014672", "by": "InTheArena", "date": "2026-07-22", "stance": "neutral", "quote": "nemotron is decent", "excerpt": "I have a DGX and a Ryzen AI Max 395 - while I love both of them, there are a few critical things that leave the DGX in use, while the Ryzen \"just\" is my primary homelab server. The biggest thing is prefil numbers, and the performance impact of higher context sizes. Qwen 27b is a great model, nemotron is decent, gemma is workable. But all of them need reasonable context for reasonable outputs. Unfortunitly, as others ", "context": "", "use_case": "local LLM", "switched_from": "", "story": "Nvidia DGX Spark as a daily driver"}, {"id": 783431009, "item_id": 48964438, "url": "https://news.ycombinator.com/item?id=48964438", "by": "shade", "date": "2026-07-18", "stance": "recommend", "quote": "it works well", "excerpt": "Nice - I'm definitely going to take a look at this. I've built my own cross-platform (Mac/Win/Linux) live captioning app on top of Nemotron, and it works well but dealing with ONNX is kind of annoying. With this having Rust support (I built it on Rust/Tauri) it should be a pretty solid candidate; I'll have to see if I can find a Silero VAD implementation that doesn't depend on ONNX, or maybe I'll see if the clankers ", "context": "built a cross-platform live captioning app", "use_case": "live captioning app", "switched_from": "", "story": "Transcribe.cpp"}, {"id": 777986000, "item_id": 48624125, "url": "https://news.ycombinator.com/item?id=48624125", "by": "vcryan", "date": "2026-06-21", "stance": "warn", "quote": "Yesterday I used the latest one on OpenRouter and it was bad - worse than StepFun", "excerpt": "Maybe I'll give Nemotron another try. Yesterday I used the latest one on OpenRouter and it was bad - worse than StepFun", "context": "", "use_case": "trying model via OpenRouter", "switched_from": "", "story": "Apertus \u2013 Open Foundation Model for Sovereign AI"}, {"id": 775862721, "item_id": 48491420, "url": "https://news.ycombinator.com/item?id=48491420", "by": "aesthesia", "date": "2026-06-11", "stance": "recommend", "quote": "Olmo and to a lesser extent Nemotron are what you should look at", "excerpt": "If you really want to see fully open training pipelines for modern LLMs, Olmo and to a lesser extent Nemotron are what you should look at. https://github.com/allenai/OLMo https://github.com/NVIDIA-NeMo/Nemotron", "context": "", "use_case": "fully open LLM training pipelines", "switched_from": "", "story": "Open Reproduction of DeepSeek-R1"}]}