MikeTrendsTrends right now
AI: reposAPI

search

local AI models

Trends

  1. 1
    Running Qwen 3.8 Flash Next on a single RTX 4090●Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/sYhnSportFootball81612 min ago

    A newly shared open-source project claims to run Alibaba's Qwen 3.8 Flash Next, a 125-billion-parameter model, on a single consumer RTX 4090 GPU at around 100 tokens per second. If the benchmarks hold up, it would make very large language models practical for hobbyists and local inference without datacenter hardware. Developers in the discussion are examining the approach and questioning the real-world performance figures.

  2. 2
    Janus tool runs GGUF models on any GPU via Vulkan●Show HN: Janus – Go binary that runs GGUF models via Vulkan on AMD/Intel/NvidiaYhnTechnologySemiconductors1048 min ago

    A new open-source project called Janus has been released on GitHub, offering a single Go binary that runs GGUF-format language models through Vulkan graphics drivers. It works across AMD, Intel and Nvidia hardware without needing CUDA or vendor-specific toolchains, and it drew early attention and discussion among developers on Hacker News.

  3. 3
    Antirez releases local inference engine for DeepSeek models●antirez/ds4⬢github21112 min ago

    Salvatore Sanfilippo, the creator of Redis known as antirez, has released ds4, a local inference engine for DeepSeek 4 Flash and PRO models. The project, written in C, supports Metal, CUDA and ROCm, meaning it runs on Apple, Nvidia and AMD hardware. It is drawing attention as a lightweight option for running the Chinese models entirely on local machines.

  4. 4
    Developer turns iPhone into second GPU for MacBook AI speedups●I made my iPhone a second GPU for my MacBook-Qwen 3.8 27B prefills 29–44% fasterYhnSportCricket3710 min ago

    A developer has shared a method of using an iPhone as a secondary GPU for a MacBook, reporting that Qwen 3 27B model prefill speeds improve by 29–44%. The trick routes the phone's hardware alongside the laptop's chip when running local language models. The claim has drawn attention from people experimenting with local AI setups and squeezing more performance out of consumer hardware.

  5. 5
    Redis creator launches ds4 for running LLMs locally●From the creator of Redis; run LLM locally with ds4YhnTechnologyAI35915 min ago

    Salvatore Sanfilippo, the creator of Redis, has released ds4, a tool for running large language models locally on a computer. The project, hosted at dwarfstar.sh, is drawing attention on Hacker News, where it has attracted several hundred upvotes. Commenters are discussing what the database pioneer's move into local AI tooling could mean for the space.

  6. 6
    Open-Source Tool Lets Users Run AI Locally▼Open-Source Tool Runs AI Locally✉newsTechnologySoftware12 min ago

    An open-source tool has been highlighted for allowing users to run artificial intelligence models directly on their own machines, without relying on cloud services. Coverage in the open-source software community points to growing interest in local AI for privacy, cost savings, and independence from major providers. Enthusiasts say the approach puts control of data and computing back in users' hands.

  7. 7
    Free tool helps estimate GPU memory needed to run AI locally●Quanta memoria serve per far girare un'IA in locale? Uno strumento gratuito per scegliere il server GPU https:// diggitaMmastodonTechnologySoftware112 min ago

    A new free tool aims to help users work out how much GPU memory is required to run artificial intelligence models on local hardware, particularly when choosing a GPU server. It is drawing interest among hobbyists and professionals who want to self-host AI models instead of relying on cloud services, a topic of growing debate as local AI deployments become more practical.

  8. 8
    India seeks deeper access to Anthropic's advanced AI models▼India wants deeper access to Anthropic’s advanced models✉newsBusinessBanking18 min ago

    India is pressing for expanded access to Anthropic's advanced AI models, according to The Banker. The report highlights growing tensions between national ambitions to build AI capacity and the controlled release policies of leading US artificial intelligence firms. New Delhi's interest reflects its broader push to secure cutting-edge AI tools for domestic development, as governments worldwide negotiate with a small group of frontier model providers over access, pricing and local deployment.

  9. 9
    Google Maps Scraper MCP Tool Unveiled●Show HN: Google Maps Scraper MCPYhnBusiness1027 min ago

    A developer has released a Google Maps Scraper MCP server, a tool that lets AI models and applications pull business data such as names, addresses, reviews and contact details directly from Google Maps. The launch drew attention on Hacker News, where users are weighing its usefulness for lead generation and local data projects against questions about scraping terms of service and Google's restrictions.

Repos