updated to single server

2026-07-15 10:30:35 +02:00
parent a08333b70a
commit a993838826
4 changed files with 63 additions and 61 deletions
@@ -0,0 +1,26 @@
+manager:
+  memory_budget: 450
+  contention_policy:
+    strategy: wait_then_preempt
+    wait_timeout_s: 45
+    preempt_after_s: 15
+
+models:
+  - name: Qwen-Coder-Next
+    model: mlx-community/Qwen3-Coder-Next-4bit
+    estimated_memory_gb: 50
+    reasoning_parser: qwen3
+
+  - name: Qwen3.6
+    model: mlx-community/Qwen3.6-35B-A3B-6bit
+    estimated_memory_gb: 40
+    reasoning_parser: qwen3
+
+  - name: gemma
+    model: mlx-community/gemma-4-31b-it-8bit
+    estimated_memory_gb: 40
+    reasoning_parser: gemma4
+
+  - name: MiniMax-M3
+    model: pipenetwork/MiniMax-M3-MLX-mixed-3_6bit
+    estimated_memory_gb: 200