--- title: Granite Switch 4.1: Chat, Decisions, and Speech from One... description: IBM's Granite Switch 4.1 release combines a base language model with multiple lightweight adapters (Activated LoRAs) to handle chat, decision-making, safety... canonical: https://daily.dev/posts/granite-switch-4-1-chat-decisions-and-speech-from-one-endpoint-0ig1nmhow twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint | daily.dev og:description: IBM's Granite Switch 4.1 release combines a base language model with multiple lightweight adapters (Activated LoRAs) to handle chat, decision-making, safety... og:url: https://daily.dev/posts/granite-switch-4-1-chat-decisions-and-speech-from-one-endpoint-0ig1nmhow og:image: https://api.daily.dev/og/posts/0ig1nmhow.png og:image:alt: Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint **[Hugging Face](https://daily.dev/sources/huggingface)** · 4 min read · 1 upvotes · 1 comments ## Summary IBM's Granite Switch 4.1 release combines a base language model with multiple lightweight adapters (Activated LoRAs) to handle chat, decision-making, safety guardrails, and speech-to-text transcription all from a single hosted endpoint, using roughly the same VRAM as the base model alone. The 8B and 30B models ship with a general-purpose Decision adapter, a Guardian safety adapter claimed to outperform several competing decision models (Jev, Microsoft-Decision-1, GPT-Luna-Decisions, Clef-Flash), and the Granite-Speech-5.0-Turbo-CTC ASR model, reportedly the fastest on the OpenASR leaderboard. Because adapters share the base model's KV cache, switching between tasks is fast and cheap, and developers can compose custom Switch models from a Granite Libraries adapter catalog. A demo shows a 3B adapter-equipped model playing Doom at 60-100 decisions per second versus a competitor's reported 10 decisions per second, while also narrating gameplay. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Granite Switch 4.1 and how does it combine chat, decisions, and speech in one model? Granite Switch 4.1 is an IBM model architecture that composes a frozen base model with multiple Activated LoRA (aLoRA) adapters for chat, decision-making, and speech recognition, all served from one endpoint. The 8B and 30B versions include a general Decision adapter, a Guardian safety adapter, and the Granite-Speech-5.0-Turbo-CTC ASR model, sharing the base model's KV cache so adding capabilities costs almost no extra VRAM. _daily.dev surfaces releases like this for engineers weighing multi-task adapter setups against separate specialized models._ ### How fast is Granite-Speech-5.0-Turbo-CTC compared to other ASR models? Granite-Speech-5.0-Turbo-CTC is described as the fastest automatic speech recognition model on the OpenASR Leaderboard. It is a 470M parameter CTC-based model embedded directly into Granite Switch 4.1 for transcription tasks, running alongside chat and decision capabilities on the same endpoint without significant additional GPU memory. _Developers comparing ASR models for production pipelines track leaderboard-topping releases like this on daily.dev._ ### Why are Activated LoRAs (aLoRAs) more efficient than regular LoRA adapters for multi-task inference? Activated LoRAs are cache-efficient adapters that let a model reuse the KV cache generated during base model inference for subsequent adapter-based decisions, avoiding recomputation when switching tasks. Combined with recent vLLM kernel contributions for low-rank adapter inference, this lets a single endpoint switch between chat, decision, and speech requests at high speed without reprocessing context. _Teams optimizing inference costs for multi-adapter LLM deployments follow efficiency techniques like this on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@ahmetozel** · 0 upvotes > Sharing the base KV cache is the architectural detail I would measure separately from the adapter’s classification speed. A mixed speech, chat, and decision workload can have different queueing behavior from an isolated five-step RAG demonstration, even when the adapters add little model memory. > > A useful deployment benchmark would interleave long transcriptions with short decisions and report decision tail latency as concurrency rises. I would also state which prefix and adapter activation point make cache reuse valid. That gives operators a way to distinguish savings from reusable context,... ## Similar posts on daily.dev - [Granite 4.0 1B Speech: Compact, Multilingual, and Built for the Edge](https://daily.dev/posts/granite-4-0-1b-speech-compact-multilingual-and-built-for-the-edge-djlhogrk3) · Hugging Face · 22 upvotes · 0 comments - [Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC](https://daily.dev/posts/extremely-fast-and-accurate-transcription-with-granite-speech-5-0-turbo-ctc-ivnplcd09) · Hugging Face · 1 upvotes · 0 comments - [granite-speech-4.1-2b, kanana-2-30b-a3b-instruct, and OpenFold3 models now available on Amazon SageMaker JumpStart](https://daily.dev/posts/granite-speech-4-1-2b-kanana-2-30b-a3b-instruct-and-openfold3-models-now-available-on-amazon-sagem-r0wd728ga) · AWS · 4 upvotes · 1 comments --- Tags: [#speech-recognition](https://daily.dev/tags/speech-recognition), [#vllm](https://daily.dev/tags/vllm), [#lora](https://daily.dev/tags/lora) [View this post on daily.dev](https://daily.dev/posts/granite-switch-4-1-chat-decisions-and-speech-from-one-endpoint-0ig1nmhow) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint","url":"https://daily.dev/posts/granite-switch-4-1-chat-decisions-and-speech-from-one-endpoint-0ig1nmhow","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/granite-switch-4-1-chat-decisions-and-speech-from-one-endpoint-0ig1nmhow"},"datePublished":"2026-10-15T20:34:25.261Z","dateModified":"2026-10-15T20:47:44.139Z","description":"IBM's Granite Switch 4.1 release combines a base language model with multiple lightweight adapters (Activated LoRAs) to handle chat, decision-making, safety...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/18897c4ee74e52fabfd1c739a5d2cc90?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/18897c4ee74e52fabfd1c739a5d2cc90?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hugging Face","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hugging Face","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f1f55c67d81a4330acf5b90b26b0c8e1","url":"https://daily.dev/sources/huggingface"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/granite-switch-4-1-chat-decisions-and-speech-from-one-endpoint-0ig1nmhow","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"speech-recognition,vllm,lora","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hugging Face","item":"https://daily.dev/sources/huggingface"},{"@type":"ListItem","position":3,"name":"Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/granite-switch-4-1-chat-decisions-and-speech-from-one-endpoint-0ig1nmhow","comment":[{"@type":"Comment","text":"Sharing the base KV cache is the architectural detail I would measure separately from the adapter’s classification speed. A mixed speech, chat, and decision workload can have different queueing behavior from an isolated five-step RAG demonstration, even when the adapters add little model memory.\nA useful deployment benchmark would interleave long transcriptions with short decisions and report decision tail latency as concurrency rises. I would also state which prefix and adapter activation point make cache reuse valid. That gives operators a way to distinguish savings from reusable context, faster adapter execution, and simply running a lighter workload.","datePublished":"2026-10-15T20:56:31.474Z","url":"https://daily.dev/posts/0ig1nmhow#c-L5Tg3Py5X","author":{"@type":"Person","name":"Ahmet Özel","url":"https://daily.dev/ahmetozel","image":"https://avatars.githubusercontent.com/u/70992231?v=4"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/granite-switch-4-1-chat-decisions-and-speech-from-one-endpoint-0ig1nmhow#faq","mainEntity":[{"@type":"Question","name":"What is Granite Switch 4.1 and how does it combine chat, decisions, and speech in one model?","acceptedAnswer":{"@type":"Answer","text":"Granite Switch 4.1 is an IBM model architecture that composes a frozen base model with multiple Activated LoRA (aLoRA) adapters for chat, decision-making, and speech recognition, all served from one endpoint. The 8B and 30B versions include a general Decision adapter, a Guardian safety adapter, and the Granite-Speech-5.0-Turbo-CTC ASR model, sharing the base model's KV cache so adding capabilities costs almost no extra VRAM. daily.dev surfaces releases like this for engineers weighing multi-task adapter setups against separate specialized models."}},{"@type":"Question","name":"How fast is Granite-Speech-5.0-Turbo-CTC compared to other ASR models?","acceptedAnswer":{"@type":"Answer","text":"Granite-Speech-5.0-Turbo-CTC is described as the fastest automatic speech recognition model on the OpenASR Leaderboard. It is a 470M parameter CTC-based model embedded directly into Granite Switch 4.1 for transcription tasks, running alongside chat and decision capabilities on the same endpoint without significant additional GPU memory. Developers comparing ASR models for production pipelines track leaderboard-topping releases like this on daily.dev."}},{"@type":"Question","name":"Why are Activated LoRAs (aLoRAs) more efficient than regular LoRA adapters for multi-task inference?","acceptedAnswer":{"@type":"Answer","text":"Activated LoRAs are cache-efficient adapters that let a model reuse the KV cache generated during base model inference for subsequent adapter-based decisions, avoiding recomputation when switching tasks. Combined with recent vLLM kernel contributions for low-rank adapter inference, this lets a single endpoint switch between chat, decision, and speech requests at high speed without reprocessing context. Teams optimizing inference costs for multi-adapter LLM deployments follow efficiency techniques like this on daily.dev."}}]} ```