by Meta AI

Llama 3.2 1B.

text open weights edge 1B params 128K ctx Transformer
Cheapest input
$0.027/M
on OpenRouter
Cheapest output
$0.06/M
on Together AI
Smallest GPU
1× Nvidia GeForce RTX 3050
$0.022/hr

Meta's smallest Llama — mobile + on-device target.

Smallest GPU to run it See all quantisations →

1× Nvidia GeForce RTX 3050 · $0.022/hr.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.027 $0.201 Launch ↗
Together AI hosted inference $0.06 $0.06 Launch ↗
Sources

Official references.

Family

Variants in the Llama family.

Best for

Workloads.

FAQ

Frequently asked.

How do I run Llama 3.2 1B?
Llama 3.2 1B is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Llama 3.2 1B?
Llama 3.2 1B is available via Hugging Face Inference, Together AI, OpenRouter, Ollama. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Llama 3.2 1B?
API pricing starts at $0.027/M input tokens and $0.201/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Llama 3.2 1B open-source or proprietary?
Llama 3.2 1B is open-weight under the Llama 3.2 Community License license. You can download and self-host it.