--- title: "17,000 Tokens/Second Inferencing of an AI Model 🤯" url: https://daily.dev/posts/17-000-tokens-second-inferencing-of-an-ai-model--zuxfvd38l source_url: https://www.youtube.com/watch?v=iComSUz5RxU type: video:youtube source: "Execute Automation" published: 2026-05-31T07:48:32.000Z updated: 2026-05-31T09:14:39.967Z tags: ["llm"] reading_time: 6 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # 17,000 Tokens/Second Inferencing of an AI Model 🤯 **[Execute Automation](https://daily.dev/sources/executeautomation)** · 6 min read · 0 upvotes · 0 comments ## Summary Talis, a hardware startup, claims their custom silicon achieves ~17,000 tokens/second inference speed for the Llama 3.1 8B model — reportedly 10x faster than Nvidia H200/B200 GPUs at 20x lower infrastructure cost. A live demo shows ~15,500 tokens/second generating Playwright/Selenium C# test code nearly instantly. The video argues ultra-fast inference will dramatically accelerate AI agent workflows, potentially compressing 20-30 minute multi-agent tasks into seconds. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [The path to ubiquitous AI](https://daily.dev/posts/the-path-to-ubiquitous-ai-rr89jl4iq) · Hacker News · 2 upvotes · 0 comments - [How Taalas "prints" LLM onto a chip?](https://daily.dev/posts/how-taalas-prints-llm-onto-a-chip--dh6pmssjy) · Hacker News · 0 upvotes · 0 comments - [Breaking the Speed Limit: Strategies for 17k Tokens/Sec Local Inference](https://daily.dev/posts/breaking-the-speed-limit-strategies-for-17k-tokens-sec-local-inference-rf86u4kz7) · SitePoint · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/17-000-tokens-second-inferencing-of-an-ai-model--zuxfvd38l)