Models & Labs
Granite Switch 4.1.1 patches adapters without retraining base
Hugging Face Bloghigh confidence
Why it matters
- →Modular architectures enable incremental updates without retraining foundational models.
- →Reduces compute costs by isolating changes to specific adapter components.
- →Sets a precedent for software-like versioning in AI model deployment.
IBM has released Granite Switch 4.1.1, a patch update for its modular language model architecture that updates specialized adapters without retraining the base model. The release includes an updated multilingual speech-to-text model supporting ten languages with native punctuation and an improved decision adapter on the Jev Decision Index test set. Because the base model remains unchanged, the update is fully backwards compatible and requires no migration. IBM plans to release an Adapter SDK to allow third-party developers to build and iterate on their own adapters.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Model Context Protocol Update Eases AI Integration
TechCrunch AI · July 20, 2026 · Background
- 2Granite 4.2 LLMs Introduced by IBM and Hugging Face
Hugging Face Blog · August 25, 2026 · Related
- 3IBM releases Granite Time Series PatchTST-FM-r2 model
Hugging Face Blog · September 9, 2026 · Background
More from Hugging Face Blog
© Hugging Face BlogAgentsagents
NVIDIA Nemotron powers interactive Halloween agent
An NVIDIA engineer built a fully local voice agent for a Halloween attraction using the new Nemotron Voice Agent framework. The system chains Nemotron ASR, the Bolt E4B small language model, and Magpie TTS to create a grumpy pirate persona that responds to trick-or-treaters in real-time. Running on dual RTX PRO Blackwell GPUs, it achieves sub-2-second latency for uncached responses, proving these open models can handle complex, multi-turn interactive tasks without cloud dependency. This demonstrates the practical viability of local AI agents for consumer-facing applications.
Hugging Face Blog
© Hugging Face BlogGeneral AIresearch
Project ProtoStar launches to make public science AI-ready
Hugging Face and a coalition of major universities are launching Project ProtoStar to solve the 'last mile' problem of scientific data: making it machine-actionable. With $190 billion in annual U.S. federal R&D funding, the initiative pushes institutions like CMU and Purdue to release datasets in standardized formats rather than static files. The kickoff challenge tests AI's ability to predict urban climate conditions using historical weather records from 210 cities. This shifts the focus from mere publication to actual interoperability, creating a reusable infrastructure for AI-driven discovery.
Hugging Face Blog
© Hugging Face BlogCoding Toolscoding
Hugging Face brings open ASR and decision models to Swift
Hugging Face is bridging the gap between Apple’s native Speech framework and the broader open-source ecosystem with AnySpeechRecognizer. By wrapping NVIDIA’s Parakeet and Alibaba’s Qwen3-ASR in a familiar Swift API, they let developers swap out Apple’s default engine for polyglot or dialect-specific alternatives without rewriting code. The package also adds speaker diarization via NVIDIA’s Sortformer, a feature missing from Apple’s native tools. This moves local inference on macOS/iOS from experimental to practical by standardizing how open models integrate with system-level audio pipelines.
Hugging Face Blog
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
Apple Intelligence arrives in China via iOS 27.3
Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.
The Verge AI
© Matt WolfeModels & Labsmodels
Google Releases Gemini 4 Carbon for Cost-Efficient Inference
Google launched Gemini 4 Carbon, a new model variant aimed at providing high performance at a lower cost for inference tasks.
Matt Wolfe