llama3.2:1b

Family context: Llama 3.2 text-model family

Publisher: Meta

Meta documents pretrained and instruction-tuned multilingual text models in 1B and 3B classes for dialogue, retrieval and summarization.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published family information

Published full-checkpoint size table

1.23B and 3.21B parameters Source

Published full text checkpoint context

128k tokens, publisher notation Source

Separate publisher quantized checkpoint context

8k tokens, publisher notation Source

Input/output role

Text and code; not the separate Llama vision releases Source

Publisher-described uses

• Multilingual dialogue, retrieval-assisted and summarization applications. Source

Reference limitations

• The publisher’s full and quantized releases have different documented limits. A local quantization tag alone does not establish which upstream artifact or configured context was used. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• Llama 3.2 text-model family official documentation — Meta. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Meta AI — official site
• Ollama
• Provider page
• Hugging Face
• Official model announcement / documentation

Where llama3.2:1b comes from

Named in 3 observation pages

• GPU adds three new notable observations · V2
• Sub-3B local models — all 34 · V1
• The Behavior Map — observed dimensions per model · V1