Preserve desktop VRAM reserve and portable CPU compression setup

libexec/hermes-stack-llama-profile

@@ -8,10 +8,10 @@ runner="$(dirname -- "${BASH_SOURCE[0]}")/hermes-stack-llama-run"
 case "${1:-list}" in
   list)
     printf '%-12s %8s %10s\n' Profil Kontext Fit-MiB \
-      baseline 65536 1536 vram-64k 65536 1280 \
+      desktop-64k 65536 4096 baseline 65536 1536 vram-64k 65536 1280 \
       balanced 49152 1536 vram-plus 49152 1280 compact 32768 1536
     exit 0 ;;
-  baseline|vram-64k|balanced|vram-plus|compact) selected="$1" ;;
+  desktop-64k|baseline|vram-64k|balanced|vram-plus|compact) selected="$1" ;;
   *)
     printf 'Unbekanntes Profil. Verfügbare Profile: %s list\n' "$0" >&2
     exit 2 ;;

libexec/hermes-stack-llama-run

@@ -72,7 +72,10 @@ fi
 
 profile_args=()
 if [[ -n "${LLAMA_PROFILE:-}" ]]; then
+  reasoning_budget=512
+  reasoning_preserve=--reasoning-preserve
   case "$LLAMA_PROFILE" in
+    desktop-64k) ctx=65536; margin=4096; reasoning_budget=128; reasoning_preserve=--no-reasoning-preserve ;;
     baseline) ctx=65536; margin=1536 ;;
     vram-64k) ctx=65536; margin=1280 ;;
     balanced) ctx=49152; margin=1536 ;;
@@ -86,7 +89,7 @@ if [[ -n "${LLAMA_PROFILE:-}" ]]; then
 
   profile_args=(
     --ctx-size "$ctx" --parallel 1 --jinja
-    --reasoning auto --reasoning-budget 512 --reasoning-preserve
+    --reasoning auto --reasoning-budget "$reasoning_budget" "$reasoning_preserve"
     --flash-attn auto --threads 6 --threads-batch 16
     --n-gpu-layers auto --fit on --fit-target "$margin"
     --cache-type-k q8_0 --cache-type-v q8_0