Meet FreeToken: An Edge-Native MoE Serving Engine that Runs 753B GLM-5.2 on a Single Workstation GPU
Source: MarkTechPost Frontier open-weight models are shipping faster than the hardware assumptions around them. Kimi-K3, GLM-5.2 and DeepSeek-V4-Flash...
The Developer’s Guide to NeMo Guardrails for Enterprise AI Safety
Source: MarkTechPost In this tutorial, we build an in-depth NeMo Guardrails pipeline that demonstrates how layered guardrails can...
Decoding AI’s Open-Source Course Maps Three Ways to Run an Agent Loop and the Provider Economics Behind Each
Source: MarkTechPost Most teams treat ‘which model’ as the important decision. The harness engineering literature keeps pointing somewhere...
Building Agentic Document Intelligence Pipelines: Creating Scientific Figures with AutoFigure
Source: MarkTechPost In this tutorial, we explore AutoFigure as a practical toolkit for generating scientific figures directly from...
Meet S1-mini: Superwhisper’s 462 MB Open-Weights Text Normalizer That Turns Raw ASR Transcripts Into Clean Written Text
Source: MarkTechPost Superwhisper has released the S1 family of models: S1-Voice, S1-Language, and S1-mini. S1-Voice is a cloud...
Meet UPDF: A Lightweight Adobe Alternative Built for the Agentic Era
Source: MarkTechPost PDFs sit at the end of almost every workflow. Contracts, invoices, research papers, scanned intake forms,...
Liquid AI Releases LFM2.5-DSpark Draft Models That Deliver Up to 3.18x Faster Decoding Without Changing Model Outputs
Source: MarkTechPost Liquid AI has released DSpark draft model checkpoints for three models in its LFM2.5 family: LFM2.5-1.2B-Instruct,...
NVIDIA Releases TensorRT Model Connect in Public Preview: Hugging Face Checkpoint to Native C++ Inference in Two Commands
Source: MarkTechPost NVIDIA has released TensorRT Model Connect (TRTMC) in public preview, an open-source project that takes a...
Meet SAM (Sovereign Agent Mesh): A Zero-Config, Zero-Trust P2P Network for AI Agents
Source: MarkTechPost google/sam is not Segment Anything. SAM here means Sovereign Agent Mesh, an Apache-2.0 networking project for...
Cartesia Ships Sonic-3.6: A Streaming TTS Model That Now Leads Both Artificial Analysis Speech Arenas
Source: MarkTechPost Cartesia has released Sonic-3.6, the newest version of its real-time text-to-speech model. It arrives roughly three...