Granite 3.3

What is Granite 3.3?

Granite 3.3 is IBM's open-weights language model. Released in 2024-12, it ships in 2 sizes (2B, 8B) and is licensed Apache 2.0. The most popular use case is enterprise on-prem with Apache 2.0 license.

VRAM and hardware

The smallest 2B size needs at least 2 GB VRAM; the largest 8B needs around 2 GB.

Size	Min VRAM (Q4_K_M)	Recommended VRAM	Tokens/sec on 3090
2B	2 GB	3 GB	~31 tok/s
8B	6 GB	9 GB	~24 tok/s

How to run Granite 3.3 locally

Option 1: Ollama (simplest)

ollama pull granite-3-3
ollama run granite-3-3

Option 2: Mullama (production)

mullama pull granite-3-3
mullama run granite-3-3

Option 3: llama.cpp (CLI)

# Download a GGUF from Hugging Face (search "granite-3-3 gguf")
./llama-cli -m granite-3-3.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("granite-3-3.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

What you can build with Granite 3.3

• enterprise RAG
• code
• tools

Hardware it fits on

• Apple Silicon (8GB): 2B in MLX
• Apple Silicon (16GB): 8B in MLX
• Apple Silicon (32GB): 8B in MLX or GGUF
• Apple Silicon (64GB+): 8B in MLX
• RTX 3090 (24GB): 8B at Q4_K_M
• RTX 4090 (24GB): same as 3090, ~30% faster
• RTX 5090 (32GB): 8B at Q8_0
• 2× RTX 6000 Ada (96GB total): 8B at Q4_K_M

Related models in the Granite family

This is the only Granite-family model in the catalog right now.

Other models you might consider

• Llama 3.1 (Meta) — 8B, general-purpose chat, agentic workflows, code
• Llama 3.2 (Meta) — 1B, low-end hardware, mobile, edge deployment
• Llama 3.2 Vision (Meta) — 11B, vision + chat on desktop GPUs
• Llama 3.3 (Meta) — 70B, best-in-class 70B for desktops
• Llama 4 (Meta) — Scout 17B (109B MoE), vision + long context (10M tokens)
• Qwen 2.5 (Alibaba) — 0.5B, strongest 7B-32B on consumer hardware