Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-02-23 · source-backed
Streams model layers through GPU memory via PCIe with an optional NVMe-to-GPU bypass. Runs Llama 3.1 70B on a single RTX 3090 (24GB VRAM). Warning: NVMe bypass mode can brick your drive — never use on your boot drive. Non-bypass mode alone is a serious consumer-hardware inference option.
Clone it: github.com/xaskasdf/ntransformer | C++, CUDA
Each link below shares sources, entities, or timing with this story.
For about a year, "run your agent locally" meant accepting a model that couldn't reliably call a tool twice in a row. That excuse is gone. Meta Superintelligence Labs published Muse Glimmer today: a 29.6B dense causal transformer, 52 layers, 6,656 hidden dim, with a ~1.8B ViT-...
PR #19378 landed in llama.cpp this week, and I think most people are underselling what it means. Backend-agnostic tensor parallelism via --split-mode tensor makes multi-GPU inference work across AMD, Intel, and Apple Silicon. Not just CUDA. Everything. For context: llama.cpp h...
Hugging Face published its Summer 2026 State of Open Models report on August 14, and one statistic in it went almost entirely unremarked in the coverage. By July 2026, agents rather than humans became the Hub's primary users. Claude Code alone accounted for 44.4% of all agent...
Celerp is a self-hosted desktop ERP covering inventory, invoicing, purchasing, manufacturing, accounting, and CRM (FastAPI + FastHTML + embedded Postgres, BSL-1.1 core with MIT modules, 521 commits). Preloop runs GitHub Actions locally or self-hosted in isolated microVMs. Lect...
An open-weight Chinese frontier model is now a dropdown option in Microsoft's coding product. That happened before anyone finished characterizing what the model does. GitHub's changelog dated August 6 makes Kimi K3 generally available across Copilot Pro, Pro+, Max, Business an...
Meta formally pivoted from open-weight Llama to fully proprietary Muse Spark, its first model from the newly formed Meta Superintelligence Labs. No downloadable weights. No self-hosting. Cloud-only private API preview to select partners. More locked down than OpenAI or Anthrop...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.