TinyLlama

What TinyLlama is for

TinyLlama is a general-purpose open-weights model from TinyLlama team, released in 2024-01 with a single 1.1B size and 2K of context, licensed Apache 2.0. The catalogue records its strength as tiny chat on any hardware.

Sizes and memory

The 1.1B needs about 1 GB of weights at Q4_K_M. That is the whole range; there is no larger or smaller variant in this record. 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
1.1B	1 GB	2 GB	NVIDIA Jetson Orin Nano 8GB

Hardware that runs TinyLlama

Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of TinyLlama at Q4_K_M. The cheapest that does is the NVIDIA Jetson Orin Nano 8GB at about $199, running the 1.1B.

The largest size any of them holds is the 1.1B at 1 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 TinyLlama: chat, edge, IoT, Raspberry Pi. It is tagged chat, small, edge, lightweight.

Where TinyLlama sits in the Llama family

Our catalogue holds 7 Llama entries. Ordered by release date, TinyLlama (2024-01) is the 2nd of them, and Llama 4 (2025-04) is newer.

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: 2K

2K tokens is a short window by 2026 standards — on the order of 2,000 words at the usual three-quarters-of-a-word-per-token ratio. That is one conversation turn with a document, not a session with a codebase. Anything longer has to be retrieved and injected rather than held.

How to run TinyLlama 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 TinyLlama 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 "TinyLlama 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.