# Granite 3.1 2B: RAM and VRAM requirements

> Granite 3.1 2B is a 2.53B Granite model. At Q4_K_M it needs about **2.8 GB** to run and fits **39 of 39** tracked devices. Minimum to run: Apple M1 (8GB).

Last validated: 2026-06-15. Sources: Ollama, HuggingFace GGUF repos, vendor specs.

## Memory by quantization
| Quant | On disk | To run (4k context) |
| --- | --- | --- |
| Q4_K_M | 1.55 GB | ~2.8 GB |
| Q8_0 | 2.69 GB | ~3.9 GB |

Memory = weights + KV cache + ~0.8 GB runtime overhead, and varies ±15% with context length.

## Will it run on my device?
- **Apple M1 (8GB)** (8 GB): Yes, it runs — room for Q8_0
- **Generic Android Phone (8GB RAM)** (8 GB): Yes, it runs — room for Q8_0
- **iPhone 17 Pro** (12 GB): Yes, it runs — room for FP16
- **Nvidia GeForce RTX 4080 (16GB)** (16 GB): Yes, it runs — room for FP16
- **Google Pixel 10 Pro** (16 GB): Yes, it runs — room for FP16
- **Nvidia GeForce RTX 4090 (24GB)** (24 GB): Yes, it runs — room for FP16
- **Apple M4 Pro (48GB)** (48 GB): Yes, it runs — room for FP16
- **Apple M3 Ultra (256GB)** (256 GB): Yes, it runs — room for FP16

Full table of all 39 devices: https://localmodel.run/model/granite-3.1-2b

## How to run
Quickest path: `ollama run granite3.1-dense:2b`. On Mac, LM Studio (ships MLX) is fastest; on Linux, Ollama for chat or vLLM to serve; on Windows, LM Studio or Ollama.

## Details
- Parameters: 2.53B
- Default context: 128k tokens
- License: Apache-2.0 (commercial use: yes)
- Released: 2024-12-18
- HuggingFace: 13,340 downloads/mo, 56 likes

## FAQ
### How much VRAM or RAM does Granite 3.1 2B need?
About 2.8 GB at Q4_K_M (weights 1.55 GB + KV cache + overhead) at a 4k context. Budget ~3.9 GB for Q8_0.
### Can Granite 3.1 2B run on a laptop?
Yes. Granite 3.1 2B fits on a 16 GB laptop or Mac at Q4_K_M, and runs on Apple Silicon or a 12 GB+ GPU comfortably.
### Can I use Granite 3.1 2B commercially?
Yes, Apache-2.0 permits commercial use.

Sources: https://ollama.com/library/granite3.1-dense:2b, https://huggingface.co/bartowski/granite-3.1-2b-instruct-GGUF, https://community.ibm.com/community/user/blogs/nickolus-plowden/2025/01/12/granite-31-delivers-powerful-performance-longer-co, https://huggingface.co/ibm-granite/granite-3.1-2b-instruct
More: https://localmodel.run/model/granite-3.1-2b