IBM · granitemoe
Can I run granite3-moe?
The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.
1.3B parameters4K contexttextApache License12 builds
granite3-moe system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| granite3-moe:1b-instruct-q4_0 | Q4_0 | 0.7 GB | ~1.5 GB(est.) |
| granite3-moe:1b | Q4_K_M | 0.8 GB | ~1.5 GB(est.) |
| granite3-moe:1b-instruct-q5_K_M | Q5_K_M | 0.9 GB | ~1.7 GB(est.) |
| granite3-moe:1b-instruct-q6_K | Q6_K | 1.0 GB | ~1.9 GB(est.) |
| granite3-moe:1b-instruct-q8_0 | Q8_0 | 1.3 GB | ~2.3 GB(est.) |
| granite3-moe:3b-instruct-q4_0 | Q4_0 | 1.8 GB | ~3.0 GB(est.) |
| granite3-moe:3b | Q4_K_M | 1.9 GB | ~3.1 GB(est.) |
| granite3-moe:3b-instruct-q5_K_M | Q5_K_M | 2.2 GB | ~3.6 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run granite3-moe locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run granite3-moe:1b-instruct-q4_0 - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about granite3-moe
- How much VRAM do I need to run granite3-moe?
- At 4K context, the smallest published build of granite3-moe (Q4_0) needs roughly 1.5 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run granite3-moe without a dedicated GPU?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 1.5 GB of free RAM for the smallest build.
- How big is the granite3-moe download?
- The smallest published build is 0.7 GB. There are 12 builds in total, the largest being 6.3 GB. Leave some extra free disk space beyond the download itself.
- How do I run granite3-moe locally?
- Install Ollama, then run "ollama run granite3-moe:1b-instruct-q4_0" in a terminal. The weights download on first use and an interactive session opens.
Will granite3-moe run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Model data from the official Ollama registry · verified 13/09/2026