Experimental Ollama compatibility with DeepSeek-Coder

1. Install Ollama

macOS / Linux — one line:

curl -fsSL https://ollama.com/install.sh | sh

On macOS you can also download the .dmg from ollama.com. On Windows, use the official installer.

2. Pull DeepSeek-Coder

Grab a model sized for your hardware. Start with the 16B variant — it fits on 16 GB of unified memory and gives you a practical starting point for review quality:

ollama pull deepseek-coder-v2:16b

On a workstation with 24 GB+ VRAM, pull a higher-quality quant:

ollama pull deepseek-coder-v2:16b-lite-instruct-q6_K

Ollama serves on http://127.0.0.1:11434 by default. Confirm with ollama list.

3. Smoke-test the endpoint

Confirm the OpenAI-compatible route is live before wiring anything else up:

curl http://127.0.0.1:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-coder-v2:16b",
    "messages": [
      { "role": "user", "content": "Review this diff: - return x + 1\n+ return x - 1" }
    ]
  }'

4. Point NeonDiff at Ollama

Install NeonDiff, initialize a local config, and complete mandatory API-backed activation before provider or review work. Pass the activation key only from an approved secret store over bounded stdin:

curl -fsSL https://www.neondiff.com/install | sh
neondiff init --config config.local.json
security find-generic-password -s YOUR_APPROVED_SOURCE -w | neondiff license activate --config config.local.json --license-key-stdin true --json

Then enable the local provider in config.local.json. Ollama on loopback normally uses authMode: "none"; do not invent a fake provider key:

{
  "providers": {
    "providers": {
      "ollama-local": {
        "enabled": true,
        "adapter": "openai-compatible",
        "baseUrl": "http://localhost:11434/v1",
        "model": "deepseek-coder-v2:16b",
        "authMode": "none",
        "structuredOutputMode": "ollama-format-json-schema",
        "capabilities": {
          "review": true,
          "jsonOutput": true,
          "local": true,
          "streaming": false
        }
      }
    }
  }
}

neondiff providers doctor --config config.local.json --provider ollama-local --smoke true --json

The Ollama compatibility interface is experimental in v1.0.4; it is not yet a promoted live-review claim. The ZCode-backed live engine remains the promoted review lane while the local adapter completes its promotion and evidence work. Use provider doctor as a compatibility smoke only, keep posting disabled, and follow the current provider-status documentation before relying on Ollama for review output.

5. Run a dry-run review

Keep posting disabled until activation, GitHub App readiness, and the selected provider smoke all pass. Then run one current-head dry run:

neondiff doctor github --config config.local.json --json
neondiff review-pr --config config.local.json --repo owner/project --pr 42 --dry-run true

Tuning notes

• Context window. DeepSeek-Coder V2 handles ~128k tokens; keep per-file review chunks under ~8k for latency.
• Quantization. Q4 for laptops, Q6 for GPU workstations, Q8 if you have the VRAM. Higher quants noticeably reduce false-positive nits.
• Warm the model. Ollama unloads models after idle; a nightly cron with a dummy request keeps first-review latency low.

FAQ