{"slug": "openvino", "name": "OpenVINO", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 6, "warners": 1, "score": 1.627, "rising": -0.98, "first": "2026-02-08", "latest": "2026-09-17", "why": "the performance through their tools is really good", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 3, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "the performance through their tools is really good", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/intel/openvino-ai-video-retrieval-analysis", "official_url": "https://docs.openvino.ai/", "pricing": "", "aliases": ["OpenVINO"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 776006099, "item_id": 48500381, "url": "https://news.ycombinator.com/item?id=48500381", "by": "dlcarrier", "date": "2026-06-11", "stance": "recommend", "quote": "the performance through their tools is really good", "excerpt": "I have an Intel A770, because at $200 USD it was the second cheapest way to get 16 of dedicated VRAM. (The cheapest is a $100 Radeon Instinct Mi25, but it's a bit old and slow.) I battled with Python packages a lot to get a1111 working, gave up when it broke on an update and switched to ComfyUI which has worked great. I can't get Llama.cpp to use the GPU, but I'm currently installing some of Intel's proprietary OpenV", "context": "", "use_case": "LLM on Intel GPU", "switched_from": "", "story": "Ask HN: What computer are you using for AI coding tools?"}, {"id": 760222880, "item_id": 47513930, "url": "https://news.ycombinator.com/item?id=47513930", "by": "martz", "date": "2026-03-24", "stance": "recommend", "quote": "this can be done locally https://github.com/intel/openvino-ai-video-retrieval-analysis", "excerpt": "this can be done locally https://github.com/intel/openvino-ai-video-retrieval-analysis", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Gemini can now natively embed video, so I built sub-second video search"}, {"id": 750945152, "item_id": 46934072, "url": "https://news.ycombinator.com/item?id=46934072", "by": "nerdsniper", "date": "2026-02-08", "stance": "recommend", "quote": "with OpenVINO than it is to figure out how to use the Apple NPU's", "excerpt": "I use pretty much all platforms and architectures as my \"daily drivers\" - x64, Apple Silicon, and ARM Cortex, with various mixtures of Linux/Mac/Windows. When Apple released Apple Silicon, it was a huge breath of fresh air - suddenly the web became snappy again! And the battery lasted forever! Software has bloated to slow down MacBooks again, RAM can often be a major limiting factor in performance, and battery life i", "context": "", "use_case": "", "switched_from": "", "story": "Why E cores make Apple Silicon fast"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 779223056, "item_id": 48701441, "url": "https://news.ycombinator.com/item?id=48701441", "by": "dlcarrier", "date": "2026-06-27", "stance": "warn", "quote": "I have the wrong Linux version to run their binaries", "excerpt": "I have a 16 GB Intel A770 and before that used an AMD Mi25. I've had SDXL stable diffusion working on both, but struggled to get LLMs going. The entire field of software development is already well known for its technical debt and lack of interest in testing (see also: https://xkcd.com/2030/), but anything having to do with AI brings it to an all new level. You pretty much need to run the same stack the developer use", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Running local LLMs? What's your model and hardware"}]}], "who": [], "tags": [], "use_cases": ["intel model compilation", "llm on intel gpu", "local object detection inference"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49724881", "title": "Nvidia announces native GPU programming in Rust", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49274152", "title": "Sharding a 70B model across 39 Intel laptops", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48698057", "title": "Ask HN: Running local LLMs? What's your model and hardware", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48498766", "title": "Ask HN: What computer are you using for AI coding tools?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47503617", "title": "Show HN: Gemini can now natively embed video, so I built sub-second video search", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47298743", "title": "My Homelab Setup", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"recommend": 1}, "2026-03": {"neutral": 1, "recommend": 1}, "2026-04": {}, "2026-05": {}, "2026-06": {"recommend": 1}, "2026-07": {}, "2026-08": {"neutral": 1}, "2026-09": {"neutral": 1}, "2026-10": {}}, "quotes": [{"id": 795931604, "item_id": 49745725, "url": "https://news.ycombinator.com/item?id=49745725", "by": "jacobgorm", "date": "2026-09-17", "stance": "neutral", "quote": "Candle on MacOS and OpenVINO on Windows", "excerpt": "As it happens, I just got my employer's permission to release as open source a Triton back-end for Metal and D3D12 GPUs here: https://github.com/dropbox/neso . As an example of you how can use it to deploy real models there is this project doing ASR and TTS: https://github.com/dropbox/nspeech . Finally, I am also going to be switching the inferencing part of Witchcraft from current Candle on MacOS and OpenVINO on Win", "context": "", "use_case": "", "switched_from": "", "story": "Nvidia announces native GPU programming in Rust"}, {"id": 788386449, "item_id": 49274153, "url": "https://news.ycombinator.com/item?id=49274153", "by": "tatef", "date": "2026-08-12", "stance": "neutral", "quote": "pre-compiled them to OpenVINO IR graphs", "excerpt": "Hey everyone, we\u2019ve been working on a project called https://cascadia.to which allows you to shard LLMs across Intel-based machines and perform inference across CPUs/GPUs/NPUs. To get it functioning, we split models into shards and pre-compiled them to OpenVINO IR graphs. Since then, we\u2019ve been working on a lot of optimizations to make sharding and running models on Intel much more performant. Most of our initial imp", "context": "", "use_case": "Intel model compilation", "switched_from": "", "story": "Sharding a 70B model across 39 Intel laptops"}, {"id": 779223056, "item_id": 48701441, "url": "https://news.ycombinator.com/item?id=48701441", "by": "dlcarrier", "date": "2026-06-27", "stance": "warn", "quote": "I have the wrong Linux version to run their binaries", "excerpt": "I have a 16 GB Intel A770 and before that used an AMD Mi25. I've had SDXL stable diffusion working on both, but struggled to get LLMs going. The entire field of software development is already well known for its technical debt and lack of interest in testing (see also: https://xkcd.com/2030/), but anything having to do with AI brings it to an all new level. You pretty much need to run the same stack the developer use", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Running local LLMs? What's your model and hardware"}, {"id": 776006099, "item_id": 48500381, "url": "https://news.ycombinator.com/item?id=48500381", "by": "dlcarrier", "date": "2026-06-11", "stance": "recommend", "quote": "the performance through their tools is really good", "excerpt": "I have an Intel A770, because at $200 USD it was the second cheapest way to get 16 of dedicated VRAM. (The cheapest is a $100 Radeon Instinct Mi25, but it's a bit old and slow.) I battled with Python packages a lot to get a1111 working, gave up when it broke on an update and switched to ComfyUI which has worked great. I can't get Llama.cpp to use the GPU, but I'm currently installing some of Intel's proprietary OpenV", "context": "", "use_case": "LLM on Intel GPU", "switched_from": "", "story": "Ask HN: What computer are you using for AI coding tools?"}, {"id": 760222880, "item_id": 47513930, "url": "https://news.ycombinator.com/item?id=47513930", "by": "martz", "date": "2026-03-24", "stance": "recommend", "quote": "this can be done locally https://github.com/intel/openvino-ai-video-retrieval-analysis", "excerpt": "this can be done locally https://github.com/intel/openvino-ai-video-retrieval-analysis", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Gemini can now natively embed video, so I built sub-second video search"}, {"id": 756919937, "item_id": 47307496, "url": "https://news.ycombinator.com/item?id=47307496", "by": "acidburnNSA", "date": "2026-03-09", "stance": "neutral", "quote": "With openvino frigate can still do fully local object detection", "excerpt": "Ryzen 5950x cpu, 64 gb ecc ram, dual 16 tb drives for zfs, Nvidia 5070 gpu. Way way overspeced for what I listed, but I use it for lots of video processing, numerical simulations, and some local AI too. I have a similar subset of this stuff running at my mom's house on a 16 GB ram Beelink minicomputer. With openvino frigate can still do fully local object detection on the security case, whish is sweet.", "context": "", "use_case": "Local object detection inference", "switched_from": "", "story": "My Homelab Setup"}, {"id": 750945152, "item_id": 46934072, "url": "https://news.ycombinator.com/item?id=46934072", "by": "nerdsniper", "date": "2026-02-08", "stance": "recommend", "quote": "with OpenVINO than it is to figure out how to use the Apple NPU's", "excerpt": "I use pretty much all platforms and architectures as my \"daily drivers\" - x64, Apple Silicon, and ARM Cortex, with various mixtures of Linux/Mac/Windows. When Apple released Apple Silicon, it was a huge breath of fresh air - suddenly the web became snappy again! And the battery lasted forever! Software has bloated to slow down MacBooks again, RAM can often be a major limiting factor in performance, and battery life i", "context": "", "use_case": "", "switched_from": "", "story": "Why E cores make Apple Silicon fast"}]}