Try Delta
← All models

IBM2026

Granite 4.1

Enterprise open · text & vision

IBM’s Granite 4.1 open models for enterprise text and multimodal work. Sized from 3B to 30B so teams can keep sensitive workloads on hardware they control.

  • Fits fromPhone / edge · 6 GB+
  • Contextup to 131K
  • Sizes3
  • RunsLocal on Delta
ReasoningVisionMultilingualEnterprise chatPrivate workloadsVision + text

Sizes

Granite 4.1 3B

2.1 GB • 131k ctx • Q4_K_M

Granite 4.1 8B

5 GB • 131k ctx • Q4_K_M

Granite 4.1 30B

18 GB • 131k ctx • Q4_K_M

Memory at context length

Approximate working set for Granite 4.1 3B as context grows.

4K
2.6 GB
8K
2.8 GB
16K
2.9 GB
33K
3.1 GB
66K
3.3 GB
131K
3.4 GB

Related families

Granite 4.2

IBM Granite 4.2 series: native reasoning capabilities for stronger local problem-solving.

Qwen3.5

A natively multimodal daily driver: text, vision, and compact reasoning on your machine.

Qwen 3.8

Qwen 3.8 Distill models: highly efficient and capable models optimized for edge and desktop.