Granite 3.3

What Granite 3.3 is for

Granite 3.3 is trained for code. IBM released it in 2024-12 with 2 sizes (2B, 8B), 128K of context and a Apache 2.0 licence. Context length matters more here than for chat, because a coding assistant that cannot see the whole file is guessing. The catalogue records its strength as enterprise on-prem with Apache 2.0 license, and it is the class of model an editor plugin such as Continue or Tabby points at.

Sizes and memory

The 2B needs about 2 GB of weights at Q4_K_M and the 8B about 6 GB, a spread of 4 GB across the family. The catalogue's default pick is 8B. Recommended VRAM adds roughly half again on top of the weights for the KV cache and the runtime.

Size	Weights at Q4_K_M	Recommended VRAM	Smallest card in our guide that holds it
2B	2 GB	3 GB	NVIDIA Jetson Orin Nano 8GB
8B	6 GB	9 GB	NVIDIA Jetson Orin Nano 8GB

Hardware that runs Granite 3.3

Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of Granite 3.3 at Q4_K_M. The cheapest that does is the NVIDIA Jetson Orin Nano 8GB at about $199, running the 8B.

The largest size any of them holds is the 8B at 6 GB, on the NVIDIA Jetson Orin Nano 8GB (8 GB at 68 GB/s). Bandwidth, not capacity, sets the speed once a size fits, so a card further down the list with faster memory will generate more tokens per second on the same weights than a larger, slower one.

What people use it for

The catalogue lists 3 recorded uses for Granite 3.3: enterprise RAG, code, tools. It is tagged enterprise, code, tools, RAG.

Where Granite 3.3 sits in the Granite family

Granite 3.3 is the only Granite entry in our catalogue, so there is no in-family alternative to weigh it against; the comparison to make is against the models listed at the foot of this page.

The Apache 2.0 licence puts no usage ceiling on it, which matters if the thing you are building has users. That is the practical difference between this and a vendor community licence.

Context window: 128K

128K tokens is roughly 96,000 words at the usual ratio, which is a small repository or a whole book. Two cautions come with a window this size: the KV cache at full length can rival the weights for memory, and models rarely use the far end of their advertised context as well as they use the near end. Treat it as headroom, not as a promise.

How to run Granite 3.3 locally

Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.

Option 1: Ollama (simplest)

# find the tag for Granite 3.3 at ollama.com/library
ollama run <tag>

Option 2: Mullama (production)

mullama pull <tag>
mullama run <tag>

Option 3: llama.cpp (CLI)

# download a GGUF from Hugging Face, searching for "Granite 3.3 GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"

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

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

Sources

Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.