Own your intelligence. Anyone that opposes this has something to sell you (perhaps your own intelligence back to you.) Local models need to continue proliferating. The “absolute unit” massive models may be out of reach for now locally, so your best option is to, indeed, keep your options open. Own your harness, data, connections, runtime: your agents. Embrace open source.

We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog:

CAREFUL ‼️ Linux and DGX Spark users: turning off MPTCP isn't enough for CVE-2026-98432 (CVSS 9.8). The bug is in the plain IPv4 TCP handshake on every unpatched kernel since 4.4. Ubuntu hasn't shipped a fix, and none is in progress for the Spark's kernel yet. What to do 👇

Kimi K3 NVFP4 on an odd cluster {GB300, RTX6000, 8 x DGX Spark} Early vllm vs tensorfold; thanks Ash! (Tensorfold decodes 2.5x faster) Interesting read for me; my agent, Milo wrote it up.

MiniMax M3.1 Flash, on more of your hardware. Quantizing a 428B model opens up more ways to run it locally. Lower-bit weights reduce the memory needed to load the model and the weight data moved during decoding. Making those savings useful takes careful calibration, efficient low-bit kernels, and hardware-aware placement of experts across GPU and system RAM. Thank you to the builders doing that work: • @UnslothAI @danielhanchen — 2-bit Dynamic GGUF weights at 143.9 GB, with calibration and fidelity testing across coding, tool use and other workloads. • @ViC305 — SAGE-EXL3, token-level fidelity measurements and a single-DGX-Spark recipe. • @PeasantSmith — Project Maya quants and expert offloading for local coding and tool use. • @MiaAI_lab — EXL3-EAQ quantization work. • @jundotkim + mlx-community — oQ quants and DSpark-powered decoding through oMLX on Apple Silicon. • @AIatAMD — Quark MXFP4 adapted for AMD Instinct. • @atomic_chat_hq — GGUFs for local desktop workflows. • @superalesha — custom inference work combining quantized weights, expert caching and system RAM on 4× RTX 3090. Every shared quant, kernel, measurement and recipe gives the next builder a better starting point. Thank you.

For all the DGX Spark owners who are interested in a cooling solution: 3D printable "forced induction" fan shroud for the sparks. This allows for a 120mm Noctua PPC 3000rpm fan to force air through the intake of the unit, drastically increasing airflow through the internal heatsinks. Asus GX10s ran cooler by ~19°C under heavy load. Nvidia DGX Spark ran cooler by ~10°C under heavy load. This eliminates the overheating issue, as long as you don't mind the fan noise. 3D files are on my repo