Models & Labs
IBM Releases Granite Speech 4.1 Models
Sam Witteveenhigh confidence
Why it matters
- →IBM's Granite Speech 4.1 models offer tailored solutions for different ASR needs.
- →The release emphasizes balancing accuracy, richness, and throughput.
- →It provides developers with new tools to enhance speech recognition applications.
IBM has launched its Granite Speech 4.1 models, featuring three 2B variants that balance accuracy, richness, and throughput. These models are tailored for various applications, providing developers with options to optimize for specific needs in automatic speech recognition. The release highlights IBM's focus on delivering adaptable ASR solutions. This development is poised to impact how developers integrate speech recognition into their projects, offering enhanced performance and flexibility.
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
- 1Speech Models Fail on Street Names
Together AI Blog · February 23, 2026 · Background
- 2Llama.cpp Adds Granite-Speech Support
llama.cpp Releases · May 7, 2026 · Related
- 3OpenAI Enhances API with New Voice Models
OpenAI · May 7, 2026 · Background
What happened next
- 4NVIDIA Releases Nemotron 3.5 ASR for Multilingual Streaming
Sam Witteveen · June 7, 2026 · Background
- 5Benchmarking ASR on Code-Switched Speech
Hugging Face Blog · June 9, 2026 · Background
- 6Granite Speech Plus Support Added in b9768 Release
llama.cpp Releases · June 24, 2026 · Related
- 7Qwen3.8-27B Model Explored and Optimized
Sam Witteveen · August 18, 2026 · Background
- 8Granite 4.2 LLMs Introduced by IBM and Hugging Face
Hugging Face Blog · August 25, 2026 · Related
More from Sam Witteveen
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