Falcon 3

What Falcon 3 is for

Falcon 3 is a general-purpose open-weights model from TII, released in 2024-12 with 4 sizes (1B, 3B, 7B, 10B) and 32K of context, licensed Apache 2.0. The catalogue records its strength as small efficient chat on consumer hardware.

Sizes and memory

The 1B needs about 1 GB of weights at Q4_K_M and the 10B about 7 GB, a spread of 6 GB across the family. The catalogue's default pick is 7B. 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
7B	5 GB	8 GB	NVIDIA Jetson Orin Nano 8GB
10B	7 GB	11 GB	NVIDIA Jetson Orin Nano 8GB

Hardware that runs Falcon 3

Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of Falcon 3 at Q4_K_M. The cheapest that does is the NVIDIA Jetson Orin Nano 8GB at about $199, running the 10B.

The largest size any of them holds is the 10B at 7 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 Falcon 3: chat, multilingual, edge. It is tagged chat, lightweight, multilingual.

Where Falcon 3 sits in the Falcon family

Falcon 3 is the only Falcon 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: 32K

32K tokens is about 24,000 words at the usual ratio — enough for a handful of files or a long report held whole. It is the point at which the KV cache starts to be a serious share of memory: doubling the context you actually use costs roughly double the cache, on top of the 1 GB of weights.

How to run Falcon 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 Falcon 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 "Falcon 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.