Llama 3.2 3B Instruct

Facts

Released

2024-09-18 the day the repository was first published on Hugging Face Hugging Face, read 2026-09-24

Licence

llama3.2 the licence the model card declares Hugging Face, read 2026-09-24

Open weights

Yes the weights are published in this Hugging Face repository, behind the maker's access form Hugging Face, read 2026-09-24

Parameters

3.2 billion counted from the safetensors weight files Hugging Face, read 2026-09-24

Active parameters

Unknown

Knowledge cutoff

2023-12-31 the knowledge cutoff OpenRouter lists OpenRouter, read 2026-09-24

Context window

• 131,072 tokens the maximum position embeddings in the model configuration model configuration, read 2026-09-24
• 131,072 tokens the context length OpenRouter lists OpenRouter, read 2026-09-24

Longest output

• 117,964 tokens the largest output OpenRouter's first provider allows OpenRouter, read 2026-09-24

Tool calling

• Yes the chat template in the tokenizer configuration accepts tool definitions Hugging Face, read 2026-09-24
• No OpenRouter does not list tools among the supported parameters OpenRouter, read 2026-09-24

Structured output

• Yes OpenRouter lists structured outputs among the supported parameters OpenRouter, read 2026-09-24

Reasoning controls

Unknown

Inputs and outputs

text in, text out Hugging Face, read 2026-09-24

Good for

No source names a use.

Prices

Run it on your own hardware

Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.

Start it with a local runtime

• Ollama

  ollama run hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:Q4_0

• LM Studio

  lms get unsloth/Llama-3.2-3B-Instruct-GGUF
  lms server start

• llama.cpp server

  llama-server -hf unsloth/Llama-3.2-3B-Instruct-GGUF:Q4_0 --jinja

• vLLM

  vllm serve meta-llama/Llama-3.2-3B-Instruct

• SGLang

  sglang serve --model-path meta-llama/Llama-3.2-3B-Instruct --port 30000

Use it from your harness

Set up for Kilo Gateway with the model meta-llama/llama-3.2-3b-instruct. Each endpoint page has the same setup for its own address.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "kilo": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Kilo Gateway",
      "options": {
        "baseURL": "https://api.kilo.ai/api/gateway",
        "apiKey": "{env:KILO_API_KEY}"
      },
      "models": {
        "meta-llama/llama-3.2-3b-instruct": {
          "name": "Llama 3.2 3B Instruct",
          "limit": {
            "context": 131072,
            "output": 117964
          }
        }
      }
    }
  }
}

{
  "providers": {
    "kilo": {
      "baseUrl": "https://api.kilo.ai/api/gateway",
      "api": "openai-completions",
      "apiKey": "$KILO_API_KEY",
      "models": [
        {
          "id": "meta-llama/llama-3.2-3b-instruct"
        }
      ]
    }
  }
}

Other ways to reach it

• NanoGPT, model meta-llama/llama-3.2-3b-instruct
• NovitaAI, model meta-llama/llama-3.2-3b-instruct
• OpenRouter, model meta-llama/llama-3.2-3b-instruct
• Pioneer, model meta-llama/Llama-3.2-3B-Instruct
• Ollama, model hf.co/unsloth/Llama-3.2-3B-Instruct-GGUF:Q4_0

Published results

These are results other people published. Baltor did not run them and does not rank models by them.

• Results the maker published on the model card published by meta-llama Hugging Face, read 2026-09-24