Skip to content
SLM-Works

Code Llama (7B Instruct)

Llama · ~7B parameters · 4B–12B (mid-size) · Last reviewed 2026-03-20

Why we use it

Solid code-centric teacher and baseline for developer copilots that must stay inside customer VPCs.

License summary

Derived from Llama 2 lineage with Meta license terms focused on code generation - check acceptable use for your product surface.

Typical deployment profiles

  • VPC, single GPU class
  • VPC, multi-GPU

Focus tags

  • Code

Typical use cases

  • IDE assistants
  • CI log summarization
  • SQL / DSL generation

External references

Related SLM-Works services

← Back to foundation models catalog · Insights · Glossary

Contact to validate a model choice for your environment.