IBM Granite 3.0 8B Instruct
IBM Research
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.
- Context window
- 128,000 tokens
- Input cost
- $0.00 / 1M
- Output cost
- $0.00 / 1M
- Latency (p50)
- —