llama.cpp adds MTP for the Qwen3.6 family This is a significant milestone for the local AI ecosystem. The performance jump with these changes is massive and elevates local inference on commodity hardware further. Special thanks to Aman Gupta for leading this development!

Interviewer: CPU usage jumps to 100% every night at 3:17 AM. No cron jobs, deployments or traffic spike. What are you checking first? Me: My bank account to see if the last month's salary was credited and My LinkedIn to see who's hiring, then I'm on sick leave for next 1 year.

US CPI surges to its highest since May 2023. VIX Short-Term Futures Index jumped +3.77% on the CPI release, as inflation came in above expectations. For amplified exposure to macro-driven volatility, discover Leverage Shares 2.25x Long VIX Short-Term Futures ETC.

Random CPO related names I like: - $SIVE - Foci (3363) - $TSEM - Browave (3163) - PCL (4977) - $AXTI - Msscorps (6830) - $IQE - Shunsin (6451) - Furukawa Electric (5801) - $MTSI - Nextronics (8417) - $LITE - $COHR - FitTech (6706) - $GFS - $ASX - LandMark (3081) - $SOI Disclosure: I own most, not all though.

⚠️ CPI picks up again US CPI just rose to 3.3% YoY (core 2.6%). The move is largely energy driven, with oil pushing higher, keeping inflation above target and disrupting the disinflation trend. The Fed stays in wait and see mode.

llama.cpp at 100k stars now that 90% of the code worldwide is being written by AI agents, I predict that within 3-6 months, 90% of all AI agents will be running locally with llama.cpp 😄 Jokes aside, I am going to use this small milestone as an opportunity to reflect a bit on the project and the state of AI from the perspective of local applications. There is a lot to say and discuss and yet it feels less and less important to try to make a point. Opinions about viability of local LLMs are strongly polarized, details are overlooked, the scientific approach is lacking. Arguments are predominantly based on vibes and hype waves. One thing is clear though - local LLMs are used more and more. I expect this trend to continue and likely 2026 will end up being one of the most important years for the local AI movement. I admit that I didn't expect the agentic era to come so quickly to the local LLM space. One year ago, the available models were too computationally expensive for doing long-context tasks. There wasn't an obvious path towards meaningful agentic applications. The memory and compute requirements were huge. Last summer, with the release of gpt-oss, things started to change. It was the first time we saw a glimpse of tool calling that actually works well within the resource constraints of our daily devices. Later in the year, even better models were released and by now, useful local agentic workflows are a reality. Comparing local vs hosted capabilities at a given moment of time is pointless. To try put things into perspective: - We don't need frontier intelligence to automate searches and sending emails - We don't need trillion parameter models to be able to summarize articles or technical documents - We don't need massive GPU data centers to control our home appliances or turn the lights off in the garage I believe that there is a certain level of intelligence we as humans can comprehend and meaningfully utilize to improve our working process. Beyond that level, access to more intelligence becomes unnecessary at best and counterproductive at worst. I also believe that that level of useful artificial intelligence is completely within reach locally and it has always been just a matter of implementing the right software stack to bring it to the end user. With llama.cpp, I am confident that we continue to be on the right track of building that software stack! The llama.cpp project is going stronger than ever. With more than 1500 contributors, the project keeps growing steadily. From technical point of view, I think that llama.cpp + ggml is the only solution that actually makes sense. That is, the software stack must run efficiently on every possible device, hardware and operating system. The technology is too important to be vendor-locked. It has to be developed in the open, by the community, together with the independent hardware vendors. This is the only right way to build something that will truly make a difference in the long run. I won't try to convince you about what is currently and will be possible with local AI. We will just continue to build as usual. I am confident that after the smoke clears and we look objectively at what we have built together, the benefits will be obvious to everyone. Big shoutout to all llama.cpp maintainers. I feel extremely lucky to be able to work together with so many talented contributors. Every day I learn something new and I feel there is so much more cool stuff that we are going to build. Also, I am really thankful that the project continues to have reliable partners to support it! Cheers!

With both PPI and CPI coming in hot, I see risk continuing to rise. The Fed’s hands are now tied, and rate cuts appear to be completely off the table for the foreseeable future. Interest rates have already been moving higher, and if inflation remains sticky, the market could soon begin pricing in the possibility of rate hikes. While there are currently no clear signs of a meaningful economic slowdown, persistently higher rates could ultimately lead to an “engineered” recession. Mega-cap stocks continue to lead the market, with GOOGL and NVDA showing the strongest relative performance, while META remains the clear laggard among the group. At the same time, market breadth has been deteriorating and participation continues to narrow. Currently, only 40% of Nasdaq stocks are trading above their 200-day moving average, and just 46% of S&P 500 stocks are above their 50-day line. Be careful chasing extended stocks in this environment. This may be a good time to finance risk by taking partial profits in names that have already produced solid gains and that allows you to freeroll the rest of the trade risk free.