Article complete
AI NewsMemory Lane Savings

IBM Launches Granite 4.0 Hybrid AI Models With Lower Memory and Hardware Costs

IBM stated that Granite 4.0 models reduce RAM usage by more than 70% compared to transformer-based models in tasks involving long inputs and concurrent sessions.

IBM Launches Granite 4.0 Hybrid AI Models With Lower Memory and Hardware Costs

Key takeaways

  • IBM's Granite 4.0 models cut RAM usage by over 70% compared to traditional transformer models.
  • Utilize cheaper GPUs while maintaining high performance with the new hybrid Mamba/transformer architecture.
  • Granite 4.0 is the first open model to achieve ISO 42001 certification for AI security and transparency.
  • Access Granite 4.0 models through multiple platforms, including IBM watsonx.ai and major cloud services.
  • Models are available in various sizes, accommodating different computational needs and capacities.

Takeaways drafted with AI from the article text.

According to IBM, Granite 4.0 models can run on significantly cheaper GPUs while maintaining performance. “Granite 4.0 features a new hybrid Mamba/transformer architecture that greatly reduces memory requirements without sacrificing performance,” the company said 

The models are open-sourced under the Apache 2.0 license and are the first open models to receive ISO 42001 certification, confirming alignment with international standards for AI security, governance and transparency. All Granite 4.0 checkpoints are cryptographically signed to verify provenance and authenticity.

Granite 4.0 is available through IBM watsonx.ai and platform partners, including Dell Technologies, Docker Hub, Hugging Face, Kaggle, LM Studio, NVIDIA NIM, Ollama, OPAQUE and Replicate. Access via Amazon SageMaker JumpStart and Microsoft Azure AI Foundry is planned.

The release includes Granite-4.0-H-Small (32B parameters, 9B active), Granite-4.0-H-Tiny (7B parameters, 1B active), and Granite-4.0-H-Micro (3B parameters). A conventional transformer variant, Granite-4.0-Micro, is also available for platforms that do not yet support hybrid architectures.

IBM stated that Granite 4.0 models reduce RAM usage by more than 70% compared to transformer-based models in tasks involving long inputs and concurrent sessions. “The more you throw at them, the more their advantages are apparent,” the company said.

Benchmarking showed that Granite 4.0 models outperform earlier Granite releases, with Granite-4.0-H-Small exceeding all open-weight models except Llama 4 Maverick on Stanford’s IFEval benchmark. On the Berkeley Function Calling Leaderboard v3, Granite 4.0 models kept pace with larger competitors at lower cost.

Enterprise partners, including EY and Lockheed Martin, tested Granite 4.0 before launch. IBM has also partnered with HackerOne on a bug bounty program, offering up to $100,000 for vulnerabilities or jailbreak exploits.

Training for Granite 4.0 was conducted on a 22T-token enterprise-focused corpus, with separate instruction-tuned models available today and reasoning-focused models planned later this fall. Additional releases, including Granite 4.0 Medium and Granite 4.0 Nano, are expected by year-end.

IBM said this release aims to lower barriers to entry by providing enterprises and open-source developers alike with cost-effective access to highly competitive LLMs.

Published Updated

Corrections: AIM corrects errors of fact and notes the change on the story. Spotted one? Tell the editors. Read our editorial standards.

More in this story

IBM · 5 stories
  1. Tesla Crash, NVIDIA’s Arm ‘Deal’emma, Facebook’s Clubhouse Clone & More In This Week’s Top News
  2. IBM Expands Software Availability to 92 Countries in AWS Marketplace
  3. You are here: IBM Launches Granite 4.0 Hybrid AI Models With Lower Memory and Hardware Costs
  4. Sarvam AI Launches Prism, a Jev-Like Decision Model Built on Sarvam 105B
  5. LTM Integrates AI Tool to Fix Quantum Computing Errors on IBM
About the author

Tech Journalist

Siddharth is a media graduate who loves to explore tech through journalism and putting forward ideas worth pondering about in the era of artificial intelligence.

All stories
Belamy · Daily

The day’s AI news, before your first meeting.