llm, improve the thread testing output and also make the the ansible variable is always an int.

tasks/workstation/linux/software/llm.yml

@@ -911,8 +911,8 @@
               model="qwen3.5:4b"
             fi
             # Benchmark Thread Count
-            for t in {1..{{ ansible_processor_vcpus }}}; do
+            for t in {1..{{ ansible_processor_vcpus | int }}}; do
-              echo "`date` - $t Threads`"
+              echo "`date` - Model $model w/ $t Threads`"
               curl -s http://localhost:11434/api/generate \
                 -d '{"model":"$model","prompt":"Hello","stream":false,"options":{"num_thread":$t}}' \
                 | jq .eval_count / .eval_duration