Research-Grade EdgeBench Analysis: AI Agent Benchmarking, Leaderboard Analytics, Scaling Laws, and Evaluation Metrics
Source: MarkTechPost In this tutorial, we explore EdgeBench as a practical benchmark for evaluating advanced AI agents across...
Unsloth vs Axolotl vs TRL vs LLaMA-Factory: A Fine-Tuning Framework Comparison on Speed, VRAM, and Multi-GPU
Source: MarkTechPost Four open source projects dominate LLM fine-tuning today. Unsloth, Axolotl, TRL, and LLaMA-Factory all wrap the...
Cisco Foundation AI Releases Antares: 350M and 1B Open-Weight Models That Localize Known Vulnerabilities Inside Real Codebases
Source: MarkTechPost Cisco Foundation AI has released Antares, a family of security small language models (SLMs) built for...
Poolside Releases Laguna S 2.1, an Open-Weight Agentic Coding Model Punching Above Its Weight Class on SWE-Bench Multilingual
Source: MarkTechPost Poolside has released Laguna S 2.1, a 118B-parameter open-weight model built for agentic coding. It is...
Google Releases Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber: A Cheaper, More Token-Efficient Flash Tier Built for Agentic Workloads
Source: MarkTechPost Developers building production agents need higher token efficiency, lower latency, and more reliable performance. Today, Google...
NVIDIA Releases Cosmos 3 Edge: A 4B-Parameter Open World Model That Reasons and Generates Robot Actions On-Device
Source: MarkTechPost NVIDIA has released Cosmos 3 Edge, a 4-billion-parameter open world model built to run on-device. It...
Alibaba’s Tongyi Lab Releases Qwen-Audio-3.0-TTS, a Hosted Text-to-Speech Model in Flash and Plus Tiers Across 16 Languages
Source: MarkTechPost Alibaba’s Tongyi Lab has released Qwen-Audio-3.0-TTS, a production-oriented text-to-speech (TTS) system. The model ships in two...
Someone Fine-Tuned OpenBMB’s MiniCPM5-1B on Claude Fable 5 Traces to Ship a 657MB Local Thinking Model
Source: MarkTechPost A community developer, GnLOLot, has published a 1B model that runs fully on local hardware. The...
Best Local LLMs You Can Run on a Single 24GB GPU in 2026: Qwen, Gemma, Mistral, DeepSeek Compared
Source: MarkTechPost A single 24GB card is the practical floor for serious local inference. It is enough for...
Feyn AI Releases SQRL, a Text-to-SQL Model Family That Inspects the Database Before Writing a Query
Source: MarkTechPost Most text-to-SQL systems treat the task as translation. Feyn AI (YC-backed startup) reframes it around inspection....