
Llama 3.2 3B
Llama 3.2 3B is a language model with 3B parameters from Meta. It is currently free at 1 provider with up to 80K tokens of context. Its weights are open, so it can also run locally.
- Developer
- Meta
- Parameters
- 3B
- Context
- 80K tokens
- Type
- Text
- License
- Open weights
- Free since
- September 28, 2026
Where to use Llama 3.2 3B for free
Each row is a separate free endpoint with its own limits.
| Provider | Context | Limit | Card | |
|---|---|---|---|---|
Cloudflare Workers AI @cf/meta/llama-3.2-3b-instruct |
80K | Workers Free: 10,000 Neurons/day shared across eligible models | — | Open |
Quick start
curl https://api.cloudflare.com/client/v4/accounts/ACCOUNT_ID/ai/v1/chat/completions \
-H "Authorization: Bearer $CLOUDFLARE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "@cf/meta/llama-3.2-3b-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.cloudflare.com/client/v4/accounts/ACCOUNT_ID/ai/v1",
api_key="YOUR_CLOUDFLARE_API_KEY",
)
reply = client.chat.completions.create(
model="@cf/meta/llama-3.2-3b-instruct",
messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.cloudflare.com/client/v4/accounts/ACCOUNT_ID/ai/v1",
apiKey: process.env.CLOUDFLARE_API_KEY,
});
const reply = await client.chat.completions.create({
model: "@cf/meta/llama-3.2-3b-instruct",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(reply.choices[0].message.content);Example for Cloudflare Workers AI. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.
Benchmarks
Source: Artificial Analysis · Llama 3.2 Instruct 3B
Similar free models
FAQ
Is Llama 3.2 3B free?
Yes. As of October 24, 2026, Llama 3.2 3B is free at Cloudflare Workers AI. Each provider has its own limits — see the table above.
What is the context window of Llama 3.2 3B?
The largest context among free routes is 80,000 tokens. Some providers cap it lower.
How do I call Llama 3.2 3B via API?
Use any OpenAI-compatible client with base URL https://api.cloudflare.com/client/v4/accounts/ACCOUNT_ID/ai/v1, model ID @cf/meta/llama-3.2-3b-instruct, and a Cloudflare Workers AI key.
How good is Llama 3.2 3B?
Artificial Analysis Intelligence Index: 5.7, GPQA Diamond: 26%. For comparison, the strongest free model in the catalog right now is GLM 5.3.
Is Llama 3.2 3B open-weight?
Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.