IBM releases Granite Switch 4.1 models combining chat, decisions and speech-to-text
Overview
IBM releases Granite-Switch-4.1-8B and -30B, which add a general Decision aLoRA, a Guardian aLoRA and Granite-Speech-5.0-Turbo-CTC to one model, according to a Hugging Face blog post.
The post says the three functions run through one hosted endpoint, use about the same GPU VRAM as the base model alone, and share its KV cache.
The blog post describes Granite-Speech-5.0-Turbo-CTC as the fastest ASR model on the OpenASR Leaderboard. It also says Granite-Switch-4.1-30B finished a five-step RAG workflow faster than Jev-27B. The source does not give the timing figures for that comparison.
Written by AI from the articles below · updated Oct 15, 5:02 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Hugging Face BlogOfficialGranite Switch 4.1 combines chat, decisions, and speech in one endpoint
AIIBM's Granite Switch 4.1 models, Granite-Switch-4.1-8B and -30B, add a general Decision aLoRA, a Guardian aLoRA, and Granite-Speech-5.0-Turbo-CTC, which the source calls the fastest ASR model on the OpenASR Leaderboard. All three run in one model that uses about the same GPU VRAM as the base model alone, and the adapters share its KV cache. The source says Granite-Switch-4.1-30B finished a five-step RAG workflow faster than Jev-27B.
Heat trend
- Current comparable heat
- 9
- Peak comparable heat
- 10Oct 15, 5:00 PM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.