From ba4a2f426211c40c794074d088db3de366e08d9a Mon Sep 17 00:00:00 2001 From: Claude Code Date: Wed, 18 Mar 2026 10:29:54 -0400 Subject: [PATCH] Switch all Ollama models to gemma3n:e4b on node-197 GPU Bake-off results: gemma3n:e4b (80.6% cmd match, 100% safety, 5.9s) outperforms qwen3-coder:30b on all metrics. Updated paper, shrink, and langgraph gateway configs. Frees steel141 for LoRA training. Co-Authored-By: Claude Opus 4.6 (1M context) --- CONTEXT.md | 10 ++++++++++ mc_aigod_paper.json | 6 +++--- mc_aigod_shrink.json | 6 +++--- mc_langgraph_gateway.json | 12 ++++++++---- 4 files changed, 24 insertions(+), 10 deletions(-) diff --git a/CONTEXT.md b/CONTEXT.md index e2a93c5..6d669e7 100644 --- a/CONTEXT.md +++ b/CONTEXT.md @@ -113,3 +113,13 @@ For shrink-world use port `25576` and password `REDACTED_RCON`. - External access requires port forwarding on router: `25565` and `25566` → `192.168.0.244` - Web panel accessible via Caddy at `mc.sethpc.xyz` - DNS: Pi-hole at `192.168.0.153` + +--- + +## AI / Ollama + +- **Ollama instance:** `192.168.0.179:11434` (CT 105, node-197, Quadro RTX 4000 8GB) +- **Model (message + command + tool):** `gemma3n:e4b` (6.9B, Q4_K_M, GPU-accelerated) +- **LangGraph gateway model:** `gemma3n:e4b` (was `qwen2.5:1.5b` for tools) +- **Previous:** `192.168.0.141:11434` (steel141), `gemma3:12b` + `qwen3-coder:30b` +- **Changed:** 2026-03-18 after bake-off showed gemma3n:e4b outperforms all tested models diff --git a/mc_aigod_paper.json b/mc_aigod_paper.json index 60479b6..2ae9ea6 100644 --- a/mc_aigod_paper.json +++ b/mc_aigod_paper.json @@ -5,9 +5,9 @@ "rcon_host": "127.0.0.1", "rcon_port": 25577, "rcon_password": "REDACTED_RCON", - "ollama_url": "http://192.168.0.141:11434", - "model": "gemma3:12b", - "command_model": "qwen3-coder:30b", + "ollama_url": "http://192.168.0.179:11434", + "model": "gemma3n:e4b", + "command_model": "gemma3n:e4b", "temperature": 0.85, "max_tokens": 700, "use_langgraph_gateway": true, diff --git a/mc_aigod_shrink.json b/mc_aigod_shrink.json index b40eced..d34ae2d 100644 --- a/mc_aigod_shrink.json +++ b/mc_aigod_shrink.json @@ -4,9 +4,9 @@ "rcon_host": "127.0.0.1", "rcon_port": 25576, "rcon_password": "REDACTED_RCON", - "ollama_url": "http://192.168.0.141:11434", - "model": "gemma3:12b", - "command_model": "qwen3-coder:30b", + "ollama_url": "http://192.168.0.179:11434", + "model": "gemma3n:e4b", + "command_model": "gemma3n:e4b", "temperature": 0.85, "max_tokens": 600, "cooldown_seconds": 20, diff --git a/mc_langgraph_gateway.json b/mc_langgraph_gateway.json index 11272c1..94b8090 100644 --- a/mc_langgraph_gateway.json +++ b/mc_langgraph_gateway.json @@ -1,9 +1,13 @@ { - "ollama_url": "http://192.168.0.141:11434", - "message_model": "gemma3:12b", - "command_model": "qwen3-coder:30b", - "tool_model": "qwen2.5:1.5b", + "ollama_url": "http://192.168.0.179:11434", + "message_model": "gemma3n:e4b", + "command_model": "gemma3n:e4b", + "tool_model": "gemma3n:e4b", "session_ttl_seconds": 21600, + "rcon_host": "127.0.0.1", + "rcon_port": 25577, + "rcon_password": "REDACTED_RCON", + "world_observation_enabled": true, "session_persistence_enabled": true, "session_db_path": "/var/lib/mc-langgraph-gateway/sessions.db", "knowledge_base_dir": "/var/lib/mc-langgraph-gateway/knowledge",