Skip to content
AI Model Radar

Llama 3.2 1B Instruct

meta-llama/Llama-3.2-1B-Instruct
Open Source · chat · open-weights
Open Alert me on changes
Intelligence
4.8
Context
128K
Max output
60K
Weights
Open
API $/1M
$0.03 / $0.20
Modalities
text
Released
18 Sept 2024
Intelligence Index via Artificial Analysis · 0–100, higher is better
License: llama3.2 · meta-llama/Llama-3.2-1B-Instruct
Download image Share on X Share on LinkedIn
AI summary
● machine-written

Llama 3.2 1B Instruct: 1B-parameter open-weights chat model

Llama 3.2 1B Instruct is a 1-billion-parameter instruction-tuned text generation model released by Meta in September 2024 under open-weights licensing. The model supports a 128k token context window with a knowledge cutoff of December 2023. It is positioned as a lightweight option for conversational use cases with lower computational requirements compared to larger models.

What's new
  • Released September 18, 2024 by Meta
  • Open-weights model under Llama 3.2 Community License Agreement
  • Supports 128k token context window
  • Knowledge cutoff: December 2023
  • Deployed across multiple inference providers (Novita, Featherless AI)
Best for
Lightweight conversational applicationsResource-constrained deploymentsMultilingual dialogue (English, German, French, Italian, Portuguese, Hindi, Spanish, Thai)Low-latency inference scenarios
Sources

Source: https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct