Llama 3.2 3B
LegacyAffordableRun locallyTiny 3B edge model from Meta optimized for on-device deployment.
Small footprint with surprisingly capable text generation. Superseded by Llama 4 Scout for most use cases.
▼
Llama 3.2 3B is somewhat expensive at $0.05/M tokens input and $0.34/M tokens output. The model supports a 80K context window.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Performance
Providers
Run locally
Run Llama 3.2 3B on your own computer with the Local AI Engine for free, with no rate limits and no third-party AI provider involved. idapt installs it and routes chat to your hardware automatically.
ollama pull llama3.2:3b-instruct-q4_K_M
Misc
Compare with
GPT 5.6 Solvs Llama 3.2 3BGPT 5.6 Lunavs Llama 3.2 3B
Claude Fable 5vs Llama 3.2 3BClaude Opus 4.8vs Llama 3.2 3BClaude Sonnet 5vs Llama 3.2 3BClaude Haiku 4.5vs Llama 3.2 3B
Gemini 3.6 Flashvs Llama 3.2 3BGemini 3.5 Flashvs Llama 3.2 3BGemini 3.5 Flash-Litevs Llama 3.2 3BGemma 4 31Bvs Llama 3.2 3B
Grok 4.5vs Llama 3.2 3BGrok Build 0.1vs Llama 3.2 3BGrok 4.1 Fastvs Llama 3.2 3B
Muse Spark 1.1vs Llama 3.2 3B
DeepSeek V4 Provs Llama 3.2 3BDeepSeek V4 Flashvs Llama 3.2 3B
MiniMax M3vs Llama 3.2 3B
GLM 5.2vs Llama 3.2 3B
Qwen3.7 Maxvs Llama 3.2 3BQwen3.7 Plusvs Llama 3.2 3BQwen3 Coder Nextvs Llama 3.2 3B
Nemotron 3 Ultravs Llama 3.2 3B
Mistral Small 4vs Llama 3.2 3BFrequently Asked Questions about Llama 3.2 3B▼
When was Llama 3.2 3B released?
▼
Llama 3.2 3B was released on September 25, 2024.
Who created Llama 3.2 3B?
▼
Llama 3.2 3B was created by Meta.
How much does Llama 3.2 3B cost?
▼
Llama 3.2 3B costs $0.05/M input tokens and $0.34/M output tokens.
What is Llama 3.2 3B API pricing?
▼
The Llama 3.2 3B API is priced at $0.05 per million input tokens and $0.34 per million output tokens. You can access Llama 3.2 3B through idapt.app alongside 200+ other AI models in one workspace.
Is Llama 3.2 3B a reasoning model?
▼
No, Llama 3.2 3B is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does Llama 3.2 3B support image or vision input?
▼
No, Llama 3.2 3B does not currently support image or vision input. It is a text-only model.
Does Llama 3.2 3B support audio?
▼
No, Llama 3.2 3B does not support audio input.
What is the context window of Llama 3.2 3B?
▼
Llama 3.2 3B has a context window of 80K tokens, meaning it can process approximately 60,000 words of context at once.
Is Llama 3.2 3B open source?
▼
Llama 3.2 3B is a proprietary model developed by Meta. The model weights and training data are not publicly available.
Where can I use Llama 3.2 3B?
▼
You can chat with Llama 3.2 3B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Llama 3.2 3B through Meta's own API or platform.