IBM Developer

@IBM Download Bob and try it for yourself, here: ibm.biz/~23ugoLzU8

Welcome back to a new week of Tech Terms! 🥳 This month, we'll be discussing all things related to IBM Bob, our new agentic SDLC partner. Get started with our first term, "SDLC" below. 🧵

IBM Dev Day: Bob Edition is tomorrow. Free virtual event + hackathon with $10,000 in prizes. Don't forget to sign up👇ibmdevday-bob.bemyapp.com/?utm_source=ib…

IBM has released three new non-reasoning Granite 4.1 models (30B, 8B, 3B) as open weights under Apache 2.0. All three are notably token-efficient relative to peer non-reasoning models, with the 8B standing out for its token efficiency relative to intelligence @IBM has released three new instruct models in the Granite 4.1 family: Granite 4.1 30B (15 on the Intelligence Index), Granite 4.1 8B (12), and Granite 4.1 3B (9). The release continues IBM's focus on small, efficient, and open models for enterprise and edge deployment, alongside the existing Granite 4.0 Nano family (1B and 350M variants released in October 2025). The Intelligence Index is the Artificial Analysis synthesis metric incorporating 10 evaluations covering agentic tasks, coding, and scientific reasoning. Key benchmarking results: ➤ All three Granite 4.1 models score 61 on the Artificial Analysis Openness Index, standing out among peer open weights non-reasoning models. This is driven by full open weights under Apache 2.0 plus partial disclosures across pre-training data, post-training data, and training methodology. Granite 4.1 sits well above peers like Qwen3.5 (39), Gemma 4 (39) and GLM-4.7-Flash (44), and represents a meaningful improvement over the Granite 4.0 family (56), driven by stronger methodology disclosure. Olmo 3.1 and K2 Think V2 (both 89) remain leaders as the most ‘open’ models. ➤ Granite 4.1 8B uses just 4M output tokens to run the Intelligence Index. This is ~20x fewer than Qwen3.5 9B (78M tokens), ~3x fewer than Ministral 3 8B (13M), and ~2x fewer than Gemma 4 E4B (8M). The pattern holds across the family: Granite 4.1 30B uses 4.6M output tokens (vs 7M for Gemma 4 31B and 25M for Qwen3.5 27B), and Granite 4.1 3B uses 2.7M. ➤ Token efficiency comes at the cost of intelligence relative to peer non-reasoning models. Granite 4.1 30B (15) trails leading peers like Qwen3.5 27B (37) and Gemma 4 31B (32). Granite 4.1 8B (12) trails Ministral 3 8B (15) and Gemma 4 E4B (15). Granite 4.1 3B (9) trails Gemma 4 E2B (12). ➤ Granite 4.1 30B and 3B both gain on the Intelligence Index over their Granite 4.0 predecessors. Granite 4.1 30B (15) gains 4 points over Granite 4.0 H Small (32B / 9B active, 11), with the largest gains in tool use (τ²-Bench: 42% vs 17%) and agentic tasks (GDPval-AA: 493 vs 344 Elo). Granite 4.1 3B (9) gains 1 point over Granite 4.0 Micro (8). Other information: ➤ License: Apache 2.0 (open weights, permissive commercial use) ➤ Context window: 128K tokens ➤ Availability: Granite 4.1 8B is available via @WandB ($0.05/$0.1 per 1M input/output tokens) and @replicate. Weights for all three models are available via @huggingface.

5️⃣ Open & flexible: apache 2.0, runs across watsonx, Ollama, Hugging Face, and more. Start building with Granite 4.1: ibm.co/6013EKUbz

4️⃣ Multimodal & production-ready, vision (docs/tables), speech (transcription), guardrails (risk scoring), embeddings (200+ languages).

🧵Building AI apps rarely means using just one model. Granite 4.1 brings language, vision, speech, and guardrails together—so you can build real workflows, not just demos. What devs should know.👇

@Joannespaule10 @coursera @IBM @credly Congrats! Great work!

Completed IBM Data Science (Jan 26) → AI Engineering (Apr 27).Built ML pipelines, neural networks, and a LangChain+Q&A chatbot. Now focused on LLMs, RAG, and real-world AI systems,Next: deployment.@IBMDeveloper @coursera #AIEngineering #Neurals #LangChain #RAG @IBM @credly

@if54uran Download the free trial and start building with Bob → ibm.co/6012EKYcs

So… why is everyone suddenly talking about Bob?​ ​ @if54uran shows how IBM Bob works alongside you across the full SDLC, from writing and reviewing to modernizing and deploying your code. ↓

Four days of hands‑on building with IBM experts. Ready to dive in? Register and start building → ibm.co/6017EKnhF

The IBM Dev Day: Bob Edition schedule is live.⚡ A virtual event + hackathon built around real AI workflows.

My latest article on @IBMDeveloper shows you how to automate @WildFlyAS with @ansible to create the perfect environment for Enterprise Java AI ✅ Zero manual setup ✅ Scale AI workloads instantly ✅ Production-ready automation Read more: developer.ibm.com/articles/wildf… #AI #Java #DevOps

If you’re building agents or tasks that take multiple steps, here’s how ALTK-Evolve works: ibm.biz/~7QOhfUzS1

📈 So instead of guessing every time, agents build better decision-making over time.

Why is it so hard for AI agents to remember things? Because many don’t learn from experience, they just repeat past behavior. ALTK-Evolve changes that. 🧵⬇️