fix: follow symlinks in model discovery, update model catalog

- Add -L flag to find in benchmark scripts (follows symlinks to /data/models/llms/)
- Exclude mmproj-*.gguf (vision projection files, not LLM models)
- Update configs/models.conf: remove Qwen3-Coder (user prefers Qwen3.5-35B-A3B),
  add Qwen3.5-27B-Q4_K_M and Q8_0 variant, reflect actual downloaded models

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

scripts/benchmark/run-baseline.sh

@@ -49,7 +49,7 @@ fi
 
 # Find models
 mapfile -t MODEL_PATHS < <(
-    find "$MODEL_DIR" -type f -name '*.gguf' \
+    find -L "$MODEL_DIR" -type f -name '*.gguf' -not -name 'mmproj-*' \
         \( -name '*-00001-of-*.gguf' -o -not -name '*-000*-of-*.gguf' \) \
         | sort
 )