Claims and evidence
- Released Primary source[1]page date; introduction [2]Model Release Date [4]README, Llama Models table
- Status AvailableMeta publishes no deprecation page for Llama models; the weights of both sizes are still listed in Meta's Hugging Face organisation (gated, license acceptance required) as seen on 2026-10-01. Primary source[3]
- Change · Architecture Uses a new tokenizer with a 128K-token vocabulary, which Meta says encodes text with fewer tokens, and grouped query attention in both sizes.Compared with Llama 2 Primary source[1]Model architecture
- Change · Context length Context length increased from 4K tokens for Llama 2 to 8K tokens.Compared with Llama 2 Primary source[4]README, Llama Models table
- Change · Training data Meta says pretraining used over 15 trillion tokens, about seven times the Llama 2 dataset, with four times more code.Compared with Llama 2 Primary source[1]Training data
- Change · Size Released in 8B and 70B sizes, where Llama 2 came in 7B, 13B and 70B.Compared with Llama 2 Primary source[4]README, Llama Models table
- Input text Primary source[2]Model Details, Input
- Output text, code Primary source[2]Model Details, Output
- Open weights YesWeights under the custom Llama 3 Community License (a custom commercial license per the model card), after accepting the license. Primary source[1]Try Meta Llama 3 today [3]
- Context window 8k tokens Primary source[2]Model Details table, Context length [1]Model architecture (sequences of 8,192 tokens)
- Access Open-weights download, cloud partner, consumer appConsumer access through the Meta AI assistant, which Meta says is built with Llama 3 technology. Primary source[1]introduction; What's next for Llama 3?; Try Meta Llama 3 today
Lineage
Predecessors
- Llama 2 · 18 July 2023
Successors
- Llama 3.1 · 23 July 2024
Based on
Not derived from another model.
Variants and derived
None recorded.
Siblings
None recorded.
All descendants
- Llama 3.1 · 23 July 2024
- Idefics3 · Hugging Face · August 2024
- Llama-3.1-Nemotron-51B-Instruct · NVIDIA · 23 September 2024
- Llama 3.2 · 25 September 2024
- Llama-3.1-Nemotron-70B-Instruct · NVIDIA · October 2024
- Llama 3.3 · 6 December 2024
- Sonar (February 2025) · Perplexity · 11 February 2025
- Llama-3.1-Nemotron-Nano-8B-v1 · NVIDIA · 18 March 2025
- Llama-3.3-Nemotron-Super-49B-v1 · NVIDIA · 18 March 2025
- Llama 4 Maverick · 5 April 2025
- Llama 4 Scout · 5 April 2025
- Llama-3.1-Nemotron-Ultra-253B-v1 · NVIDIA · 7 April 2025
- Llama-3.1-Nemotron-Nano-4B-v1.1 · NVIDIA · 20 May 2025
- Llama-3.3-Nemotron-Super-49B-v1.5 · NVIDIA · 25 July 2025
- Nemotron Nano 2 · NVIDIA · 18 August 2025
- Nemotron Nano 2 VL · NVIDIA · 28 October 2025
- Nemotron 3 Nano · NVIDIA · 15 December 2025
- Nemotron 3 Super · NVIDIA · 11 March 2026
- Nemotron 3 Nano 4B · NVIDIA · 16 March 2026
- Muse Spark · 8 April 2026
- Nemotron 3 Nano Omni · NVIDIA · 28 April 2026
- Nemotron 3 Ultra · NVIDIA · 4 June 2026
- Muse Spark 1.1 · 9 July 2026
- Muse Spark 1.2 · 5 August 2026
- Muse Glimmer · 10 August 2026
- Nemotron 3.5 Lightning · NVIDIA · 11 August 2026
- Muse Spark 1.3 · 2 September 2026
Variants
Meta Llama 3 8B
Same dates as Meta Llama 3.
- Variant Inline variant in this record.Released as a pretrained model (Meta-Llama-3-8B) and an instruction-tuned model (Meta-Llama-3-8B-Instruct). Primary source[1] [2]Model Details [3]
Also known as: Meta-Llama-3-8B, Meta-Llama-3-8B-Instruct, Llama 3 8B
Differs in:
- Parameters: 8B Evidence not assessed [2]Model Details table, Params
Meta Llama 3 70B
Same dates as Meta Llama 3.
- Variant Inline variant in this record.Released as a pretrained model (Meta-Llama-3-70B) and an instruction-tuned model (Meta-Llama-3-70B-Instruct). Primary source[1] [2]Model Details [3]
Also known as: Meta-Llama-3-70B, Meta-Llama-3-70B-Instruct, Llama 3 70B
Differs in:
- Parameters: 70B Evidence not assessed [2]Model Details table, Params
Related AI Radar coverage
AI Radar coverage starts in June 2026; no coverage linked yet.