feat: switch default Ollama model to gemma4:e2b

gemma4:e2b has native function calling with dedicated tool tokens, achieving 100% tool selection accuracy in benchmarks vs 67% for mistral-nemo-large, with 5-8x faster response times (2-4s vs 15-20s) and lower VRAM usage (8GB vs 9.2GB). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-04 22:44:27 +02:00
parent 4f911929f4
commit 427ad311dc
5 changed files with 555 additions and 3 deletions
@@ -17,7 +17,7 @@ PREFER_CLOUD_BACKEND=true

 # Ollama Configuration (local fallback when Claude unavailable)
 OLLAMA_HOST=http://localhost:11434
-OLLAMA_DEFAULT_MODEL=mistral-nemo:latest
+OLLAMA_DEFAULT_MODEL=gemma4:e2b
 OLLAMA_TIMEOUT=120

 # SearXNG Configuration