NEWS · MODELS · #2069
Granite Switch 4.1 integrates decision adapters and fastest OpenASR model into one endpoint
Granite Switch 4.1 (8B and 30B) bundles a general Decision aLoRA, a specialized Guardian aLoRA that the team reports outperforms several safety-focused decision models on related tasks, and Granite-Speech-5.0-Turbo-CTC (tied to the OpenASR leaderboard) into a single hosted endpoint. The adapters are cache-efficient Activated LoRAs that reuse the base model's KV cache, keeping VRAM use similar to the base model while enabling fast switching between chat, decision, and speech-to-text workloads; a Hugging Face demo (“Speech-to-Decisions”) shows real-time transcription, summaries and safety screening on one endpoint.
KEY POINTS
- Granite Switch 4.1 (8B and 30B) bundles a general Decision aLoRA, a specialized Guardian aLoRA that the team reports outperforms several safety-focused decision models on related tasks, and Granite-Speech-5.0-Turbo-CTC (tied to the OpenASR leaderboard) into a single hosted endpoint.
- The adapters are cache-efficient Activated LoRAs that reuse the base model's KV cache, keeping VRAM use similar to the base model while enabling fast switching between chat, decision, and speech-to-text workloads; a Hugging Face demo (“Speech-to-Decisions”) shows real-time transcription, summaries and safety screening on one endpoint.
- This matters because it packs chat, specialized decision-making, and high-speed ASR into one low-VRAM endpoint using reusable adapters, enabling faster multi-task workflows and easier composition of specialist adapters.
WHY IT MATTERS
This matters because it packs chat, specialized decision-making, and high-speed ASR into one low-VRAM endpoint using reusable adapters, enabling faster multi-task workflows and easier composition of specialist adapters.