Tag
IBM released Granite Speech 5.0 2B, a compact multilingual speech-language model for ASR and speech translation across six languages, with improved noise robustness, language-ID prompting, and up to 2000-keyword biasing over its predecessor.
IBM 发布 Granite Speech 5.0 系列更新，包括新的 2B 语音语言模型以及改进的 470m-turboctc 和 4.1-2b-plus 版本，在转录、翻译、抗噪和说话人归属方面更准确快速，采用 Apache 2.0 许可。
IBM 发布 Granite Switch 4.1 30B/8B，这是一个模块化 LLM，将基座模型、多个 aLoRA 适配器（决策、guardian）和语音编码器组合在一起，通过单个端点即可在聊天、通用/专业决策和语音转文本之间切换，采用 Apache 2.0 许可。
IBM releases two new compact AI models, Granite Speech 5.0 Turbo CTC, for extremely fast and accurate English speech transcription, achieving over 12,600 RTFx on NVIDIA H200 GPU.
Granite 4.2 is IBM's new family of reasoning LLMs available in 3B, 8B, and 30B sizes, featuring thinking modes, tool calling, and trained with a multi-stage reinforcement learning pipeline under the Apache 2.0 license.
Antares-1B is an open-weight, 1-billion parameter language model built on IBM Granite 4.0 for autonomous vulnerability localization in codebases. It operates as a terminal agent, outperforms much larger models on the VLoc benchmark, and is released under Apache 2.0 by Cisco.
IBM releases Granite Embedding Multilingual R2, a family of open-source multilingual embedding models under Apache 2.0, featuring a compact 97M model that achieves best-in-class sub-100M retrieval quality and a 311M model with Matryoshka embeddings, both supporting 32K context and 200+ languages.
This article details the technical architecture and training pipeline of IBM's Granite 4.1 LLMs, covering pre-training, SFT, and RL stages. It highlights that the 8B dense model outperforms larger MoE counterparts and notes the release under Apache 2.0 license.
IBM releases Granite-4.1-8B, an Apache 2.0 licensed 8B parameter long-context instruct model with enhanced tool-calling and multilingual support.
IBM releases Granite 4.0 3B Vision, a compact vision-language model designed for enterprise document understanding, featuring specialized capabilities for table extraction, chart interpretation via ChartNet, and key-value pair grounding.