IBM ResearchmodelOpen Source

IBM Granite 3.0 8B Instruct

IBM Granite 3.0 8B Instruct is a lightweight enterprise-grade language model trained on a carefully curated enterprise corpus and optimized for RAG, summarization, classification, and code generation in business contexts.

code instruct open-source long-context

Best for

Code GenerationDebuggingCode ReviewInstruction Following

ollama run ibm:granite:3:8b:instruct

Run locally

Use this model Try in Playground Compare →Alternatives →

Context Window

128K tokens ≈ 284 pages of text

Input Cost

Free

Output Cost

—

Latency p50

—

Pricing Details

Standard PricingFree tier

Input (per 1M tokens)

$0.00

Output (per 1M tokens)

$0.00

Run it locally

Local run command

ollama run ibm:granite:3:8b:instruct

Presumptive Specs:

Typical GPU

12–24 GB VRAM

System RAM

16+ GB

Disk

20+ GB free

Runtime

Docker / local runtime

Hallucination Score™ (est.)

Community reliability estimate · not official

—

Not yet rated

About this score: Community-estimated based on user reports and publicly available benchmark data (e.g. TruthfulQA). This is not an official score from the model provider. Scores may be inaccurate — always verify with the official leaderboard before making production decisions.

Price History

Not enough historical data yet. Check back after the next pricing sync.

Provider

IBM Research

Visit site

Usage & Examples

Learn how to use IBM Granite 3.0 8B Instruct

✓Complex reasoning and analysis

✓Customer support automation

✓Content generation and editing

✓Code review and debugging

✓Research summarization

💡 Tip: Start with the sample prompts above to see how IBM Granite 3.0 8B Instruct works best.

Community Prompts

Proven prompts shared by the community for this model

Loading prompts…