Llama-2-7b-chat

No priced offering is listed for this model yet.

Family

llama

Not stated on Meta’s pages: max input, input modalities, output modalities, reasoning efforts, reasoning can be off, max thinking budget, built-in tools, knowledge cutoff, licence, aliases.

• LMArena Text 1,108

  #163 of 163 listed models · CI 1,101–1,115 · 14,148 votes

• LMArena Text · Chinese 1,063

  #160 of 161 listed models · CI 1,043–1,083 · 956 votes

• LMArena Text · Coding 1,103

  #163 of 163 listed models · CI 1,089–1,117 · 1,956 votes

• LMArena Text · Creative writing 1,072

  #163 of 163 listed models · CI 1,058–1,086 · 2,341 votes

• LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 28, 2026
• changes we made

No changes recorded yet.

• Meta Model API models (opens in a new tab) dev.meta.ai · checked Oct 13, 2026
• Meta Model API: reasoning (opens in a new tab) dev.meta.ai · checked Oct 12, 2026
• meta-llama/Llama-2-7b-chat model card (opens in a new tab) huggingface.co · checked Nov 1, 2026
• meta-llama/Llama-2-7b-chat model card (opens in a new tab) huggingface.co · checked Oct 30, 2026

Meta’s official policies: data use, privacy, terms →

Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data

Meta · United States · ai.meta.com

Snapshots, the same family and other models from this provider

• Llama-3.1-70B-Instruct
• Llama-3.1-8B-Instruct
• Llama-3.2-1B-Instruct
• Llama-3.2-3B-Instruct
• Llama-3.3-70B-Instruct
• Muse Spark Open
• Muse Wonder
• Muse Wonder Full