IBM releases Granite Switch 4.1

IBM released Granite Switch 4.1 — to handle chat, judging and speech transcription from a single endpoint, it bundles the 8B and 30B models with a judging aLoRA, a Guardian aLoRA for safety judgments and Granite-Speech-5.0-Turbo-CTC

Why it matters

Because these are activated LoRAs, the KV cache built by the base model can be reused for the judgment that follows, and IBM said GPU memory with all three components added stays close to that of the base model alone. It gave almost no numerical comparisons, only a demonstration in which a customized 3B model judged 60 to 100 items per second

Source — Primary sources first; secondary reports are labelled “Press”

Officialhuggingface.cohttps://huggingface.co/blog/ibm-granite/granite-switch-4-1

Added in Week 43, 2026 · See that week

Same week

Reflection launches Beam, an open-weight modelOfficialNVIDIA previews a 2.8 trillion token corpus for 22 Indian languagesOfficialNVIDIA launches RTX Spark laptopsOfficialMeta releases Muse Spark Open weightsOfficial

Nearby on the same axis

Taking vLLM Apart: A Practical Guide to Disaggregated ServingOfficialOpenAI unveils a bundle of announcements at DevDay 2026OfficialOpenAI revamps prompt caching for GPT-6OfficialDeepSeek releases DeepSeek-V4.1-FlashPaper