作者： Jakub Rusinowski · 最后更新： 2026年7月10日
IBM's enterprise-grade model family. Granite 3.0 is Apache 2.0 licensed and rigorously trained for coding, transparency, and safety in business environments.
| Granite 3.0 8B Instruct | Min 6 GB VRAM · Q4_K_M · 4,096 ctx · ollama run granite3-dense |
The cheapest GPU that runs Granite 3.0 locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).
Install Ollama then run: ollama run granite3-dense
Minimum VRAM: 6 GB. For best results use Q4_K_M quantization.
Granite 3.0 needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Granite 3.0 8B Instruct (6 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Granite 3.0 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Granite 3.0 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run granite3-dense. This downloads Granite 3.0 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.