GLM-4.7 185B W4A16 weights reported at 92 GB
A January 3, 2026 post reports W4A16 weights for GLM-4.7 185B totaling 92 GB. The author says they ran 100 million tokens locally.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
South Korean program sets three requirements for model training
The first round will include five teams, with four advancing. Projects must train models from scratch, be partly open for commercial use, and pursue ambitious goals such as large-scale omni models.
Read articleAMD B650 chipset expansion board for Intel systems
A video documents an open-source expansion board based on the AMD B650 chipset and explores whether it can be used with an Intel motherboard.
Read articleRK182X kit pairs RK3588 modules with AI accelerators
Published on December 30, 2025, the announcement describes a kit for evaluating LLM and VLM workloads on embedded systems, using RK3588 and RK182X modules.
Read articleLisuan begins shipping 6 nm 7G100 GPUs
Chinese company Lisuan has begun shipping its 7G100 GPUs, manufactured on a 6 nm process, to initial customers. The move marks the product’s initial deployment.
Read articleMrav: custom CPU and browser playground
Published on December 30, 2025, Mrav presents a custom CPU architecture and core, with a browser IDE for writing assembly and watching registers in real time.
Read articleIntel releases HPC tuning guide for Xeon 6
On December 29, 2025, Intel released version 1.2a of its guide to tuning and optimizing high-performance computing (HPC) applications for Xeon 6 systems.
Read articleGraphcore IPUs target small batches
A post dated December 29, 2025 describes Graphcore IPUs as massively parallel accelerators suited to small batches, but difficult to use.
Read articleReview of 10GbE PCIe Gen4 x1 NICs with RTL8127
Published on December 29, 2025, the article reviews low-power 10GbE network cards with a PCIe Gen4 x1 interface and the Realtek RTL8127 chip. The available summary gives no comparative results.
Read articleURM explores recurrence and nonlinearity
A post dated December 29, 2025 describes research attributing Universal Transformers’ reasoning gains to recurrent inductive bias and strong nonlinearity. The proposed URM adds local token mixing and truncated backpropagation in recurrent loops.
Read articleBit-Brick Cluster K1 supports up to four RISC-V modules
The cluster accepts up to four SSOM-K1 modules, each with an octa-core RISC-V SpacemiT K1 processor. An integrated Gigabit Ethernet switch connects the modules, and listed operating systems include Bianbu OS, OpenHarmony, and OpenWrt.
Read articleStop hooks for keeping agents running
Published on December 27, 2025, this bookmark describes a plugin using a stop hook to ask an agent to continue after it stops. The approach may help orchestrate longer agent tasks.
Read articleSelf-play trains agents to insert and fix bugs
Published on December 26, 2025, the summary presents Self-play SWE-RL: a method for training a coding agent to insert and fix bugs in real repositories, without natural-language problem descriptions or human-labeled issues.
Read articleVL-JEPA predicts embeddings for vision and language
Published on December 26, 2025, the summary introduces VL-JEPA, a model that predicts continuous embeddings of target text instead of generating tokens autoregressively.
Read articleRadar: Linux Kernel build and boot guide
Published on December 25, 2025, this item presents an in-depth guide to Linux Kernel configuration, build systems, compilation, and boot.
Read articleIntel 64 and IA-32 manuals: architecture reference
Published on December 25, 2025, this entry highlights Intel's official manuals on the Intel 64 and IA-32 architecture and programming environment, as a primary reference for engineers working on architecture and low-level programming.
Read articleMegaRAG proposes multimodal graphs for RAG
Published on December 25, 2025, the MegaRAG abstract describes a method that automatically builds knowledge graphs from visual documents to support retrieval and cross-modal reasoning.
Read articleAgent-R1: modular training for LLM agents
Published on December 24, 2025, this summary presents Agent-R1, an end-to-end reinforcement learning framework for training LLM agents in multi-turn interactions with tools and environments.
Read articleFrom C and C++ code to an executable: compilation steps
Learn the pipeline that turns C and C++ source code into an executable: preprocessing, compilation, assembly, and linking.
Read articleKascade reuses key patterns in sparse attention
Published on December 24, 2025, the report describes a training-free method that reuses key patterns across layers. It reports speed gains on H100 GPUs and little accuracy loss on long-context benchmarks.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.