Day 15/ Nevermind, we're still cooking... and reset. Enjoy.

🥈 MiniCPM-V 4.7 just climbed to #2 on @huggingface Trending! Thank you to everyone trying the model, sharing feedback, and building with it. Your support keeps us pushing on-device multimodal AI forward. 📱 35B-A3B MoE runs smoothly on iOS and Android with ~3GB memory. The 1B model delivers strong OCR, math, and video understanding performance. Try it！ 🤗 Models: huggingface.co/collections/o… 💻 GitHub: github.com/OpenBMB/MiniCPM-V Let's keep the momentum going! 🚀

Our team worked with OpenCode to have their users who are also OpenAI API customers back in business and any credits refunded which would have been drawn in the attack. Also, you can request Daybreak Blue access to use our cyber permissive setup for defense. Do not wait until you have to deal with an incident. We’re here to help.

There's a big argument on whether you _should_ cap the clock rates on your DGX Sparks because they are, in theory, supposed to cool themselves to safe levels. NVIDIA doesn't recommend capping them, but they also don't recommend not capping them. Here's my thoughts on this: I have a couple of DGX Sparks that are marginal when running heavy prefill on GLM 5.3. This model pushes the box to the max. I'm not kidding - it jumps from ~47C to 87C in under a minute. During a heavy TP=3 prefill test, one box reliably powers itself off (!) without a clock cap. With a clock cap, it stays on. I have an additional fan moving air over the Sparks. I can add additional cooling, but this is a datapoint where NVIDIA's guidance is, in fact, wrong. Not all DGX Sparks can ramp their fans and/or throttle their own power fast enough to prevent thermal shutdown without a clock cap. 2200 MHz is enough to keep it alive. You know what? I'm happy to give up a small 1-2% gap in peak performance to keep the Sparks alive. Heat over time is one of the silent killer of chips.

I'm quickly becoming more impressed with smaller models that perform at frontier levels and more bored with giant models that I cannot run myself. At this point, I've realized I just really don't care to run the shit over an API. I would rather wait for smaller local models to catch up to the frontier. By that, I mean closing the gap between Qwen 3.8 27B/Next-Flash and the new DeepSeek v4.1. At the rate we're going, it's only a matter of time before we see that level of performance in models the size of Qwen 3.8. Remember, there are small models that beat DeepSeek R1, which was long fawned over for how good it was. Now it's beaten by a 27B model or even Nemotron at 120B. The majority of people have less than 128GB of VRAM, and it will most likely remain that way unless something happens to make VRAM unfathomably cheap. That constraint will eventually pressure developers to make better, smaller open models. There's some nuance to this, ofc.

Today, we’re releasing Bonsai 2 2B, 4B, and 9B. Based on Qwen3.5, these new ternary models bring stronger reasoning, visual understanding, and tool calling to compact footprints designed for everyday devices: • 2B: 0.43GB • 4B: 0.95GB • 9B: 2.0GB For this release, we focused on what makes small models useful as local assistants: following instructions, avoiding repetitive loops, calling tools on mobile devices, and giving useful answers without unnecessary output. The 9B model uses roughly 40% fewer tokens on standard instruction-following and everyday math tasks. Solving the Riemann hypothesis can wait. These models are successors to our first-generation Bonsai 1.7B, 4B, and 8B, and provide a foundation for bringing practical agentic functionality to local applications on personal computers, phones, and wearables. The Bonsai 2 family now includes four sizes spanning 2B to 27B parameters. Developers can choose the balance of capability, memory use, and responsiveness that fits their application and hardware. Available today under Apache 2.0.

We've made some improvements to Grok Bot’s quality, polish, and speed. Cards in chat have a new design with a cleaner layout.

Friendly reminder that Hermes was never built or intended to be exclusively for the "personal assistant" agent that can just read your emails and nothing else. I fully intend and have plainly stated many times that I always built hermes to be the most powerful AI Agent. "Normie" consumers can leverage that and we do what we can to make it an experience they can approach (the mobile app will be almost exclusively focused on consumer) - but they are not our only demographic. I want the scientists, the cybersecurity engineers, the developers, the knowledge workers, the creatives, and everyone else to be able to have an agent that they can leverage that is maximally useful to them too. Not just your mom. (She called btw you need to make your bed)

GPT-6.1 Sol takes the #2 spot in the Hermes Index.. what is your experience when it comes to GPT models?

🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4