Granite 4.1 30B
LLM Provider / Model ยท Enterprise coding with tool calling, RAG workflows, multilingual development, FIM code completions, IBM ecosystem, governed deployments
At a glance
| Input price | Free (self-hosted) |
| Output price | Free (self-hosted) |
| Price tier | Free |
| Context window | 131K |
| Max output | 16K |
| Context tier | 128K-500K |
| Speed tier | Fast |
| Latency | local-bound |
| Knowledge cutoff | 2026 |
| Modality | Text-only |
| Model ID | granite-4.1-30b |
| Provider | IBM |
| HumanEval | 88% |
| MMLU | 80% |
| Benchmark | HumanEval: high |
| Released | Apr 2026 |
| Hosting | Open-weights |
| Capabilities | Tool use, Streaming, Structured output, Function calling, FIM code completions, RAG-optimized, Multilingual (12 languages), RL alignment, Self-hostable |
What Granite 4.1 30B does
Tool use, Streaming, Structured output, Function calling, FIM code completions, RAG-optimized, Multilingual (12 languages), RL alignment, Self-hostable
Best for
Enterprise coding with tool calling, RAG workflows, multilingual development, FIM code completions, IBM ecosystem, governed deployments
Works well with
Agent / Orchestration
Conflicts & caveats
- Trae's built-in model menu may not include Granite 4.1 30B โ Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
- Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Granite 4.1 30B is not in the supported model list.
- Kiro's spec mode is tuned for Claude models โ Granite 4.1 30B may work but spec-driven flows are best with Claude.
- Cursor's built-in model menu may not include Granite 4.1 30B โ verify it's available in your Cursor model picker.
- OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family โ Granite 4.1 30B is not selectable inside this integration.
- Gemini CLI is locked to Google Gemini models โ your LLM is Granite 4.1 30B.
- Privacy conflict: Self-hosted Granite 4.1 30B sends code to cloud @codebase (Cursor). Use local context (Continue indexing, ChromaDB, LanceDB, pgvector, Vespa self-hosted) for true privacy.
- Claude Code only works with Claude models โ your LLM is Granite 4.1 30B.
- Devin uses Cognition's proprietary model internally โ your selected Granite 4.1 30B will be ignored.
- OpenAI Codex (Cloud) runs GPT-5.1 Codex internally โ your selected Granite 4.1 30B will be ignored.
- Jules runs Gemini models internally โ your selected Granite 4.1 30B will be ignored.
- The Claude Code SDK is tuned for Claude models โ Granite 4.1 30B may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
- Lovable uses a fixed internal model โ your selected Granite 4.1 30B will be ignored.
- Replit Agent 3 uses its own model selection internally โ your selected Granite 4.1 30B will be ignored.
Build a full stack around Granite 4.1 30B โ Flowpicker shows compatibility warnings before you commit.
Open the stack planner โ