Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.
If you arrived here through a search or shared link, this page collects the links I found for Locally Run for the week ending July 31, 2026.
As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.
This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Gemini 3.1 Flash Image Preview.
Category Cover Image Prompt: 1980s neo-noir movie poster of a matte primer gray 1973 Chevrolet Chevelle Malibu idling inside a cramped concrete garage with the roll-up door half-closed to a wet sodium-lit street outside, taillights bleeding deep red across the back wall where a golden-yellow neon scorpion hums above a workbench, 35mm anamorphic grain with soft halation, crushed blacks and hot magenta pink accents, the title 'Local' scrawled in handwritten magenta-pink brush script in the lower third.
This Week in Locally Run News
Summary by Claude Sonnet 5.5 based on this week’s links:
- Kimi K3 gets shrunk to run at home: Unsloth said its 1-bit Kimi K3 cut the model from 1.56TB to 594GB and keeps about 78.9% accuracy, with a Mac Studio plus 128GB RAM listed as a target. It also ran a 1-bit GGUF on 4x B200s at 36 tok/s in a four-model aquarium prompt comparison.
- Local assistants move into everyday apps: Hermes Agent added voice activation with a wake word, pitched as a replacement for Google Home or Alexa on any device that can run its GUI or CLI. Superwhisper partnered with Cohere to power local dictation with the open Transcribe model.
- Open models keep getting bigger and easier to run: Unsloth announced Inkling-Small, a 276B Apache-2.0 model from Thinking Machines that runs locally on 128GB RAM. Demis Hassabis noted Gemma 4 has passed 300M downloads, and the Gemma series as a whole is past 900M.
This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.
This week's links related to Locally Run
Hey Hermes – Replace your Google Home, Alexa, whatever you got with Hermes Agent on any device that can run the GUI or CLI locally! Voice activation is now in Hermes Agent along with many other voice chat improvements. To toggle listening for wake word on, just click the ear”
https://x.com/Teknium/status/2082510413162553674
Personal Computer is now available in the Perplexity app for Windows. Personal Computer is the local agent harness for your work. It orchestrates agents across your local files, connected apps, and the web. Research, code, browse, and build all inside one unified system.”
https://x.com/perplexity_ai/status/2082103880155046176
We’ve partnered with @cohere to bring their state-of-the-art speech recognition model, Transcribe, into Superwhisper. One of the most accurate open models in the world, now powering your dictation locally. Read more:
https://x.com/superwhisper/status/2082490678890697040
You can now run Inkling-Small, a new 276B model by Thinking Machines. Inkling-Small is the strongest open model for its size and runs local on 128GB RAM. Apache-2.0 Licensed, it has image, audio + 1M context support. Guide:
https://t.co/mwyyMtrtA9 GGUF:
https://x.com/UnslothAI/status/2082899798047563984
just to clarify: Gemma 4 models have been downloaded 300M+ times, the Gemma open model series as a whole has been downloaded an incredible 900M+ times!!”
https://x.com/demishassabis/status/2081075346208600103?s=20
How Local AI Ecosystems Are Rewriting the Global AI Assistant Race”
https://x.com/TheTuringPost/status/2081169987100623003
I’ve become extremely cloud agent-pilled. I still haven’t setup my laptop for local development since joining Cognition and it’s still unclear to me when I will have to. Working with Devin in Slack (with coworkers) and the webapp with the latest crop of models is better in every”
https://x.com/jaredpalmer/status/2082845336041587052
We compared 1-bit Kimi K3 to Claude Opus 5 and GPT 5.6. We gave 4 models the same prompt: Create a glass aquarium whose side panel develops a visible crack and then bursts. 1-bit Kimi K3 GGUF ran locally on 4x B200s at 36 tok/s. GitHub repo:
https://x.com/UnslothAI/status/2082528683747873194
Kimi K3 is now available on Ollama’s cloud. To use it with Claude Code, run: ollama launch claude –model kimi-k3:cloud Currently Kimi K3 requires a Pro or Max subscription, and consumes extra usage credits. We’re quickly working on adding capacity to expand access.”
https://x.com/ollama/status/2081771120173408767
Kimi K3 is available day-0 for on-premise deployment on @Dell Host the 2.8T frontier open intelligence in your own servers, with PowerEdge XE9780 Link to Dell Enterprise Hub below. GG @juanjucm @balaatdell @MichaelDell on the release”
https://x.com/jeffboudier/status/2081864251816231350
Indian capital should be chasing scrappy, hungry builders like this humanoid startup. Vanar Robots builds nearly the whole robot in-house, actuators, linear drives, manipulators, and structure, with materials mostly sourced locally in India (down to fishing-line tendons from”
https://x.com/TheHumanoidHub/status/2083011991313260736
LFM2.5-Encoders for Fast Long-Context Inference on CPU
https://huggingface.co/blog/LiquidAI/lfm2-5-encoders
Kimi K3 can now be run locally! ✨ The 1-bit model retains ~78.9% accuracy after we shrunk it from 1.56TB to 594GB (-62% size). Run on a Mac Studio + 128GB RAM device. Kimi K3 is the strongest open model to date. Guide:
https://t.co/1mVwOMLpDW GGUF:
https://x.com/UnslothAI/status/2082463988953367031
Running Kimi K3 on Hopper? We released an FP8-Block quantized checkpoint tuned for it. FP8 is native to Hopper’s tensor cores, so you get the throughput the H100/H200 are built to deliver. Day Zero support ready with @vllm_project. Weights – try it now:”
https://x.com/RedHat_AI/status/2082150579464188139
We signed the Open Weights letter because we believe the future of AI should be shaped by everyone, not controlled by a select few. That belief has always been at the heart of Unsloth: everyone should be able to train and run models on their own local device.”
https://x.com/UnslothAI/status/2081698818794676367
Leave a Reply