From 31be504f695e9b2ebcad0ce388e02e51bf574b8a Mon Sep 17 00:00:00 2001 From: Claude Code Date: Wed, 18 Mar 2026 10:23:55 -0400 Subject: [PATCH] Switch Ollama to gemma3n:e4b on node-197 GPU Bake-off results: gemma3n:e4b (80.6% cmd match, 100% safety, 5.9s) outperforms qwen3-coder:30b (67.7%, 93.5%, 14.7s) on all metrics. Moved from steel141 CPU inference to node-197 RTX 4000 GPU. Co-Authored-By: Claude Opus 4.6 (1M context) --- CONTEXT.md | 9 +++++++++ mc_aigod_shrink.json | 6 +++--- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/CONTEXT.md b/CONTEXT.md index e2a93c5..15c1b2c 100644 --- a/CONTEXT.md +++ b/CONTEXT.md @@ -113,3 +113,12 @@ 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 (both message + command):** `gemma3n:e4b` (6.9B, Q4_K_M, GPU-accelerated) +- **Previous:** `192.168.0.141:11434` (steel141), `gemma3:12b` + `qwen3-coder:30b` +- **Changed:** 2026-03-18 after bake-off showed gemma3n:e4b outperforms qwen3-coder:30b (80.6% vs 67.7% cmd accuracy, 100% vs 93.5% safety, 3x faster) diff --git a/mc_aigod_shrink.json b/mc_aigod_shrink.json index 1d8d9b9..5811394 100644 --- a/mc_aigod_shrink.json +++ b/mc_aigod_shrink.json @@ -5,9 +5,9 @@ "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,