$ git diff main -- deployment/air-gapped.md
True air-gap (no outbound connection for inference) is the rarest deployment shape in this market. Today only Qodosrc, DeepSource Enterprise, which publishes an airgapped deployment row and BYOK inference on your own infrastructuresrc, and SonarQube Server (rule-based core only) genuinely run air-gapped. Snyk Code and Diffblue Cover have on-prem options that may qualify depending on configuration. Augment Code used to be on this list. It publishes no self-hosted, VPC or on-prem option todaysrc.
2+DeepSource - Enterprise Server with airgapped deployment and BYOK: Claude, OpenAI or Gemini keys running inference on your own infrastructure
4+Snyk Code - on-prem broker available; check whether DeepCode AI is in or out of the air-gap perimeter
5+Diffblue Cover - generates JUnit tests, not PR review; on-prem JetBrains plugin path is the closest fit
1A single A100 80GB serves ~150 concurrent PR reviews per hour at Llama 3.3 70B-equivalent quality. For 50 devs at ~10 PRs/dev/wk that is well within capacity.
2Memory budget: a 70B model in 4-bit needs ~40GB VRAM. Pair with KV-cache headroom and you want 80GB.
3Two GPUs for redundancy. One node, one fail-over.
4-Capex caveat: A100s are still ~$10K used / $15K new at mid-2026 pricing. Air-gap inference is not cheaper than SaaS until ~200 devs.
1Llama 3.3 70B / Llama 4 70B - solid generalist for review
2DeepSeek-Coder V3 - strong on code specifically
3Qwen 3 Coder - good multilingual code coverage
1-Most teams asking for "air-gapped" really want "VPC-only with audit logs". That is much cheaper to satisfy.
2+If your security team is good faith, walk through the threat model first. Outbound-to-Anthropic with a no-training contract usually clears the bar.