Llama 3.2

What Llama 3.2 is for

Llama 3.2 is a general-purpose open-weights model from Meta, released in 2024-09 with 2 sizes (1B, 3B) and 128K of context, licensed Llama 3.2 Community License. The catalogue records its strength as low-end hardware, mobile, edge deployment.

Sizes and memory

The 1B needs about 1 GB of weights at Q4_K_M and the 3B about 2 GB, a spread of 1 GB across the family. The catalogue's default pick is 3B. 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
1B	1 GB	2 GB	NVIDIA Jetson Orin Nano 8GB
3B	2 GB	3 GB	NVIDIA Jetson Orin Nano 8GB

Hardware that runs Llama 3.2

Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of Llama 3.2 at Q4_K_M. The cheapest that does is the NVIDIA Jetson Orin Nano 8GB at about $199, running the 3B.

The largest size any of them holds is the 3B at 2 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 4 recorded uses for Llama 3.2: chat, edge, mobile, low-resource. It is tagged chat, small, mobile, tools.

Where Llama 3.2 sits in the Llama family

Our catalogue holds 7 Llama entries. Ordered by release date, Llama 3.2 (2024-09) is the 4th of them, and Llama 4 (2025-04) is newer.

The Llama 3.2 Community License is a vendor community licence rather than a standard open-source one: usable, redistributable with attribution, and carrying conditions that are worth reading before you build a product on it.

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 Llama 3.2 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 Llama 3.2 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 "Llama 3.2 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.