Audit Athena quantization inventory and runtime efficiency limits

2026-09-20 21:18:27 +02:00
parent 4007242709
commit 2425c999b0
11 changed files with 532 additions and 1 deletions
@@ -0,0 +1,38 @@
+[
+  {
+    "path": "/data/models/qwen3.8-27b-iq4-xs-pure/qwen3.8-27b-IQ4_XS-pure.gguf",
+    "bytes": 14534384640,
+    "metadata": {
+      "general.architecture": "qwen35",
+      "general.name": "Qwen3.8-27B",
+      "general.quantization_version": 2,
+      "general.file_type": 30
+    },
+    "tensor_count": 866,
+    "tensor_types": {
+      "IQ4_XS": 506,
+      "F32": 360
+    },
+    "descriptor_end": 10996711
+  },
+  {
+    "path": "/data/models/qwen3.8-27b-iq4-mix/Qwen3.8-27B-IQ4-MIX.gguf",
+    "bytes": 14111614400,
+    "metadata": {
+      "general.architecture": "qwen35",
+      "general.name": "Hf_Symlink",
+      "general.quantization_version": 2,
+      "general.file_type": 30
+    },
+    "tensor_count": 866,
+    "tensor_types": {
+      "Q5_K": 1,
+      "F32": 360,
+      "IQ2_S": 1,
+      "IQ3_S": 96,
+      "IQ4_XS": 340,
+      "Q4_K": 68
+    },
+    "descriptor_end": 10995127
+  }
+]