IBM 发布 Granite Switch 4.1：一个端点提供对话、决策与语音能力

Decision models aren’t new. Our previous release of Granite Libraries features a repository of specialized “decision model” adapters and other specialized task adapters that can be composed into custom Granite Switch models. And while Jev and other closed decision models focus on generality, we’ve found that many of our specialized granitelib adapters can outperform generalists on specialized classification tasks.

Compare granitelib adapters with generalist decision models when evaluated on specialized classification tasks.

Because adapters share the base model's KV cache, adding specialists alongside a generalist decision adapter costs almost nothing. You get broad coverage from the generalist and higher accuracy from specialists on the tasks you care about.

In a “Race” between Granite-Switch-4.1-30B (frozen base Granite + 4 specialized aLoRAs) and Jev-27B (frozen base Qwen model + 1 generic decision LoRA), Granite-Switch-4.1-30B was able to complete a real world, 5-step RAG workflow much faster than its competitor.

Granite-Switch-4.1-8B and -30B are released with “batteries included”. They are Granite Switch models that we compiled with a predefined set of helpful adapters. But you don’t need to use our version. Anyone can compose their own Granite Switch model , mixing and matching adapters from Granite Libraries to best meet their needs.

Moving forward, we see tremendous opportunity for the community to compose and extend Granite Switch models with custom and third party adapters. We plan to release an Adapter SDK for training adapters in Mellea , along side other tutorials and Granite Switch support. These adapters could be specialized classification adapters to augment decision-based workflows or adapters for specialized language tasks. You could even use custom adapters to teach a 3B parameter version of Granite to play the classic game Doom.

Similarly to Jev, our custom 3B parameter Granite Switch model made split second decisions to navigate the Doom game, but was able to do so at 60 - 100 decisions / second, compared to Jev’s reported 10 decisions / second. 1 Unlike Jev, this Granite Switch model can also narrate and respond to your questions while it is playing.

Resources for Getting Started

Granite Switch 4.1 Model Cards

Speech-to-Decisions Demo

Granite Switch GitHub Repo

Create your own aLoRA v LoRA race on Colab .

Footnotes

Models mentioned in this article 5

ibm-granite/granite-speech-5.0-470m-turboctc

ibm-granite/granite-switch-4.1-30b

ibm-granite/granite-switch-4.1-8b

ibm-granite/granitelib-core-r1.0

ibm-granite/granitelib-guardian-r1.0

Spaces mentioned in this article 3

Open ASR Leaderboard

Explore multilingual speech recognition model benchmarks

Granitelib Adapters vs Decision Models

Granite 4.1 adapters vs decision models across granitelib

Speech to Decisions with Granite

Live speech, heard and sized up by one Granite Switch model

Collections mentioned in this article 2

Granite 4.2 LLMs: How They're Built

Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC