{"slug": "taalas", "name": "Taalas", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 6, "commenters": 7, "warners": 0, "score": 5.463, "rising": -1.96, "first": "2026-02-19", "latest": "2026-07-11", "why": "which worked well and was so fast every time I've hit it this past week", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 0, "compare": 1, "warn": 0}, "spark": [0, 0, 0, 2, 1, 0, 2, 0, 1, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "which worked well and was so fast every time I've hit it this past week", "kind": "", "icon": true, "domain": "taalas.com", "github_repo": null, "official_url": "https://taalas.com", "pricing": "", "aliases": ["Taalas"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 781990016, "item_id": 48874376, "url": "https://news.ycombinator.com/item?id=48874376", "by": "skybrian", "date": "2026-07-11", "version": null, "stance": "recommend", "quote": "Taalas has a pretty impressive proof of concept", "excerpt": "Taalas has a pretty impressive proof of concept, but there's been no news about them recently. https://chatjimmy.ai/", "context": "", "use_case": "", "switched_from": "", "story": "Alex Karp Is Saying What Every Angry CEO Is Thinking About AI"}, {"id": 771915696, "item_id": 48244731, "url": "https://news.ycombinator.com/item?id=48244731", "by": "nullbio", "date": "2026-05-22", "version": null, "stance": "recommend", "quote": "They've made a hardware LLM that reaches over 14k TPS on Llama 3.1 8B", "excerpt": "Taalas: https://taalas.com/products/ They've made a hardware LLM that reaches over 14k TPS on Llama 3.1 8B, and you can try it here: https://chatjimmy.ai/ So clearly hardware LLMs are the future, and the cost will be drastically reduced. But I know that all the AI labs want to create a perception of high prices forever.", "context": "", "use_case": "", "switched_from": "", "story": "Microsoft reports AI is more expensive than paying human employees"}, {"id": 768522945, "item_id": 48032684, "url": "https://news.ycombinator.com/item?id=48032684", "by": "sunnybeetroot", "date": "2026-05-05", "version": null, "stance": "recommend", "quote": "I thought groq was fast but this is insane.", "excerpt": "Do you have more information on this? I thought groq was fast but this is insane. EDIT: it\u2019s this company https://taalas.com/products/", "context": "", "use_case": "", "switched_from": "", "story": "GPT\u20115.5 Instant"}, {"id": 755840898, "item_id": 47240056, "url": "https://news.ycombinator.com/item?id=47240056", "by": "jjcm", "date": "2026-03-03", "version": null, "stance": "recommend", "quote": "with Taalas ( https://chatjimmy.ai ) proving out that baked silicon models can be truly instant.", "excerpt": "\"Instant\" is really going to age poorly as far as a brand name goes, especially with Taalas ( https://chatjimmy.ai ) proving out that baked silicon models can be truly instant. I was literally posting about this earlier this morning[1], but all data indicates that we'll have models equivalent to Opus 4.6 / GPT 5.3 with a truly instant (ie > 10k t/s) response time by 2028. Small models are getting better faster, and t", "context": "", "use_case": "", "switched_from": "", "story": "GPT\u20115.3 Instant"}, {"id": 754358193, "item_id": 47147387, "url": "https://news.ycombinator.com/item?id=47147387", "by": "rancar2", "date": "2026-02-24", "version": null, "stance": "recommend", "quote": "which worked well and was so fast every time I've hit it this past week", "excerpt": "My attempt with trying one of their OOTB prompts in the demo https://chat.inceptionlabs.ai resulted in: \"The server is currently overloaded. Please try again in a moment.\" And a pop-up error of: \"The string did not match the expected pattern.\" That happened three times, then the interface stopped working. I was hoping to see how this stacked up against Taalas demo, which worked well and was so fast every time I've hi", "context": "", "use_case": "", "switched_from": "", "story": "Mercury 2: The fastest reasoning LLM, powered by diffusion"}]}], "caveats": [], "who": [], "tags": [], "use_cases": [], "compared": [{"slug": "llama", "name": "Llama", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48873978", "title": "Alex Karp Is Saying What Every Angry CEO Is Thinking About AI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48244434", "title": "Microsoft reports AI is more expensive than paying human employees", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48025274", "title": "GPT\u20115.5 Instant", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47236169", "title": "GPT\u20115.3 Instant", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47144464", "title": "Mercury 2: The fastest reasoning LLM, powered by diffusion", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47103661", "title": "How Taalas \"prints\" LLM onto a chip?", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"compare": 1, "recommend": 2}, "2026-03": {"recommend": 1}, "2026-04": {}, "2026-05": {"recommend": 2}, "2026-06": {}, "2026-07": {"recommend": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 781990016, "item_id": 48874376, "url": "https://news.ycombinator.com/item?id=48874376", "by": "skybrian", "date": "2026-07-11", "version": null, "stance": "recommend", "quote": "Taalas has a pretty impressive proof of concept", "excerpt": "Taalas has a pretty impressive proof of concept, but there's been no news about them recently. https://chatjimmy.ai/", "context": "", "use_case": "", "switched_from": "", "story": "Alex Karp Is Saying What Every Angry CEO Is Thinking About AI"}, {"id": 771915696, "item_id": 48244731, "url": "https://news.ycombinator.com/item?id=48244731", "by": "nullbio", "date": "2026-05-22", "version": null, "stance": "recommend", "quote": "They've made a hardware LLM that reaches over 14k TPS on Llama 3.1 8B", "excerpt": "Taalas: https://taalas.com/products/ They've made a hardware LLM that reaches over 14k TPS on Llama 3.1 8B, and you can try it here: https://chatjimmy.ai/ So clearly hardware LLMs are the future, and the cost will be drastically reduced. But I know that all the AI labs want to create a perception of high prices forever.", "context": "", "use_case": "", "switched_from": "", "story": "Microsoft reports AI is more expensive than paying human employees"}, {"id": 768522945, "item_id": 48032684, "url": "https://news.ycombinator.com/item?id=48032684", "by": "sunnybeetroot", "date": "2026-05-05", "version": null, "stance": "recommend", "quote": "I thought groq was fast but this is insane.", "excerpt": "Do you have more information on this? I thought groq was fast but this is insane. EDIT: it\u2019s this company https://taalas.com/products/", "context": "", "use_case": "", "switched_from": "", "story": "GPT\u20115.5 Instant"}, {"id": 755840898, "item_id": 47240056, "url": "https://news.ycombinator.com/item?id=47240056", "by": "jjcm", "date": "2026-03-03", "version": null, "stance": "recommend", "quote": "with Taalas ( https://chatjimmy.ai ) proving out that baked silicon models can be truly instant.", "excerpt": "\"Instant\" is really going to age poorly as far as a brand name goes, especially with Taalas ( https://chatjimmy.ai ) proving out that baked silicon models can be truly instant. I was literally posting about this earlier this morning[1], but all data indicates that we'll have models equivalent to Opus 4.6 / GPT 5.3 with a truly instant (ie > 10k t/s) response time by 2028. Small models are getting better faster, and t", "context": "", "use_case": "", "switched_from": "", "story": "GPT\u20115.3 Instant"}, {"id": 754358193, "item_id": 47147387, "url": "https://news.ycombinator.com/item?id=47147387", "by": "rancar2", "date": "2026-02-24", "version": null, "stance": "recommend", "quote": "which worked well and was so fast every time I've hit it this past week", "excerpt": "My attempt with trying one of their OOTB prompts in the demo https://chat.inceptionlabs.ai resulted in: \"The server is currently overloaded. Please try again in a moment.\" And a pop-up error of: \"The string did not match the expected pattern.\" That happened three times, then the interface stopped working. I was hoping to see how this stacked up against Taalas demo, which worked well and was so fast every time I've hi", "context": "", "use_case": "", "switched_from": "", "story": "Mercury 2: The fastest reasoning LLM, powered by diffusion"}, {"id": 753756705, "item_id": 47109794, "url": "https://news.ycombinator.com/item?id=47109794", "by": "brainless", "date": "2026-02-22", "version": null, "stance": "recommend", "quote": "I applied for Taalas API because it would be awesome fit.", "excerpt": "The trick with small models is what you ask them to do. I am working on a data extraction app (from emails and files) that works entirely local. I applied for Taalas API because it would be awesome fit. dwata: Entirely Local Financial Data Extraction from Emails Using Ministral 3 3B with Ollama: https://youtu.be/LVT-jYlvM18 https://github.com/brainless/dwata", "context": "", "use_case": "", "switched_from": "", "story": "How Taalas \"prints\" LLM onto a chip?"}, {"id": 753357488, "item_id": 47084843, "url": "https://news.ycombinator.com/item?id=47084843", "by": "nl", "date": "2026-02-19", "version": null, "stance": "compare", "quote": "Taalas's 16,000 token-per-second acceleration for the roughly comparable Llama 8B model", "excerpt": "Releasing this on the same day as Taalas's 16,000 token-per-second acceleration for the roughly comparable Llama 8B model must hurt! I wonder how far down they can scale a diffusion LM? I've been playing with in-browser models, and the speed is painful. https://taalas.com/products/", "context": "", "use_case": "", "switched_from": "", "story": "Consistency diffusion language models: Up to 14x faster, no quality loss"}]}