Local AI

Up to 3x the speed with no loss of quality—is it too good to be true?

Large language models are getting incredibly powerful, but let’s be honest—their inference speed is still a massive headache for anyone trying to use them in production. Google just launched Multi-Token Prediction (MTP) drafters for the Gemma 4 model family. This specialized speculative decoding architecture can actually triple (3x) your speed at inference time, all without […] The post Google AI Releases Multi-Token Prediction (MTP) Drafters for Gemma 4: Delivering Up to 3x Faster Inference Without Quality Loss appeared first on MarkTechPost.

DeepSeek says both models are more efficient and performant than DeepSeek V3.2 due to architectural improvements, and have almost "closed the gap" with current leading models, both open and closed, on reasoning benchmarks.

A new study of frontier models on Kalshi and Polymarket finds consistent losses, even as early signs suggest more autonomous systems could eventually outperform human bettors.

Google’s Gemma 4 comes touted as the latest evolution of Google’s multi-modal model offerings. Gemma 4 not only offers reasoning and tool use, but vision and audio functionality, and it’s available in a range of model sizes that target servers and local devices. What’s striking about Gemma 4 is that even at the higher end of its size range, it’s still decently performant on personal hardware. Google claims this is due to innovations in the architecture of the model, but the proof is in the trying. Gemma 4 is quite responsive. To that end, I took Gemma 4 for a spin on my own hardware to see how it fared for its advertised tasks. Gemma 4 model sizes Gemma 4 comes in four basic sizes or “densities”: E2B: 2.3 billion effective parameters, 5.1 billion total, 128K max context window. E4B: 4.5 billion efffective parameters, 8 billion total, 128K max context window. 31B: 31 billion parameters (the “dense” version), 256K max context window. (You will probably not use this one on your own machi

Imagine asking your AI model, “What’s the weather in Tokyo right now?” and instead of hallucinating an answer, it calls your actual Python function, fetches live data, and responds correctly. That’s how empowering the tool call functions in the Gemma 4 from Google are. A truly exciting addition to open-weight AI: this function calling is […] The post Gemma 4 Tool Calling Explained: Build AI Agents with Function Calling (Step-by-Step Guide) appeared first on Analytics Vidhya.

As the capabilities of frontier models advance, gaining access to the technology could become critically important

OpenAI is introducing sandbox execution that allows enterprise governance teams to deploy automated workflows with controlled risk. Teams taking systems from prototype to production have faced difficult architectural compromises regarding where their operations occurred. Using model-agnostic frameworks offered initial flexibility but failed to fully utilise the capabilities of frontier models. Model-provider SDKs remained closer to […] The post OpenAI Agents SDK improves governance with sandbox execution appeared first on AI News.