Harris Notes

Home

❯

entities

❯

Llama 2 7B Chat

Llama 2 7B-Chat

Apr 14, 20261 min read

  • entity
  • product
  • general

Llama 2 7B-Chat

Meta’s 7B parameter chat model; uses approximately 7GB RAM in 4-bit quantisation and has a mature ecosystem, though its non-commercial licence restricts closed-source use.

Details

  • Services: text generation, chat

Related

gguf-4-bit-quantisation local-llm-inference llama-cpp ollama meta


Graph View

  • Llama 2 7B-Chat
  • Details
  • Related

Backlinks

  • Meta
  • 20260414-1234-successes-and-risks-running-llm--locally-on-mac-mi
  • index

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community