diff --git a/common/arg.cpp b/common/arg.cpp
index 0b57f9da1..ac99e725b 100644
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -1219,9 +1219,9 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     ));
     add_opt(common_arg(
         {"--prio"}, "N",
-        string_format("set process/thread priority : 0-normal, 1-medium, 2-high, 3-realtime (default: %d)\n", params.cpuparams.priority),
+        string_format("set process/thread priority : low(-1), normal(0), medium(1), high(2), realtime(3) (default: %d)\n", params.cpuparams.priority),
         [](common_params & params, int prio) {
-            if (prio < 0 || prio > 3) {
+            if (prio < GGML_SCHED_PRIO_LOW || prio > GGML_SCHED_PRIO_REALTIME) {
                 throw std::invalid_argument("invalid value");
             }
             params.cpuparams.priority = (enum ggml_sched_priority) prio;
diff --git a/common/common.cpp b/common/common.cpp
index 4e1a020d0..26afea743 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -203,6 +203,7 @@ bool set_process_priority(enum ggml_sched_priority prio) {
 
     DWORD p = NORMAL_PRIORITY_CLASS;
     switch (prio) {
+        case GGML_SCHED_PRIO_LOW:      p = BELOW_NORMAL_PRIORITY_CLASS; break;
         case GGML_SCHED_PRIO_NORMAL:   p = NORMAL_PRIORITY_CLASS;       break;
         case GGML_SCHED_PRIO_MEDIUM:   p = ABOVE_NORMAL_PRIORITY_CLASS; break;
         case GGML_SCHED_PRIO_HIGH:     p = HIGH_PRIORITY_CLASS;         break;
@@ -228,6 +229,7 @@ bool set_process_priority(enum ggml_sched_priority prio) {
 
     int p = 0;
     switch (prio) {
+        case GGML_SCHED_PRIO_LOW:      p =  5;  break;
         case GGML_SCHED_PRIO_NORMAL:   p =  0;  break;
         case GGML_SCHED_PRIO_MEDIUM:   p = -5;  break;
         case GGML_SCHED_PRIO_HIGH:     p = -10; break;
diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp
index cbcbfcee8..3efb47120 100644
--- a/examples/llama-bench/llama-bench.cpp
+++ b/examples/llama-bench/llama-bench.cpp
@@ -266,7 +266,7 @@ static void print_usage(int /* argc */, char ** argv) {
            join(cmd_params_defaults.embeddings, ",").c_str());
     printf("  -ts, --tensor-split <ts0/ts1/..>          (default: 0)\n");
     printf("  -r, --repetitions <n>                     (default: %d)\n", cmd_params_defaults.reps);
-    printf("  --prio <0|1|2|3>                          (default: %d)\n", cmd_params_defaults.prio);
+    printf("  --prio <-1,0|1|2|3>                       (default: %d)\n", cmd_params_defaults.prio);
     printf("  --delay <0...N> (seconds)                 (default: %d)\n", cmd_params_defaults.delay);
     printf("  -o, --output <csv|json|jsonl|md|sql>      (default: %s)\n",
            output_format_str(cmd_params_defaults.output_format));
diff --git a/ggml/include/ggml.h b/ggml/include/ggml.h
index 8fcc16df9..eda1912a5 100644
--- a/ggml/include/ggml.h
+++ b/ggml/include/ggml.h
@@ -2138,6 +2138,7 @@ extern "C" {
 
     // scheduling priorities
     enum ggml_sched_priority {
+        GGML_SCHED_PRIO_LOW = -1,
         GGML_SCHED_PRIO_NORMAL,
         GGML_SCHED_PRIO_MEDIUM,
         GGML_SCHED_PRIO_HIGH,
diff --git a/ggml/src/ggml-cpu/ggml-cpu.c b/ggml/src/ggml-cpu/ggml-cpu.c
index 504003287..e3a7936dd 100644
--- a/ggml/src/ggml-cpu/ggml-cpu.c
+++ b/ggml/src/ggml-cpu/ggml-cpu.c
@@ -2417,12 +2417,30 @@ static bool ggml_thread_apply_priority(int32_t prio) {
     // This is up to the applications.
     DWORD p = THREAD_PRIORITY_NORMAL;
     switch (prio) {
+        case GGML_SCHED_PRIO_LOW:      p = THREAD_PRIORITY_BELOW_NORMAL;  break;
         case GGML_SCHED_PRIO_NORMAL:   p = THREAD_PRIORITY_NORMAL;        break;
         case GGML_SCHED_PRIO_MEDIUM:   p = THREAD_PRIORITY_ABOVE_NORMAL;  break;
         case GGML_SCHED_PRIO_HIGH:     p = THREAD_PRIORITY_HIGHEST;       break;
         case GGML_SCHED_PRIO_REALTIME: p = THREAD_PRIORITY_TIME_CRITICAL; break;
     }
 
+    if (prio != GGML_SCHED_PRIO_LOW) {
+        // Tell Windows that this thread should not be throttled (needs its own CPU core).
+	// Newer Windows 11 ARM64 versions aggresively park (offline) CPU cores and often place
+	// all our threads onto the first 4 cores which results in terrible performance with
+	// n_threads > 4
+        THREAD_POWER_THROTTLING_STATE p;
+        ZeroMemory(&p, sizeof(p));
+        p.Version     = THREAD_POWER_THROTTLING_CURRENT_VERSION;
+        p.ControlMask = THREAD_POWER_THROTTLING_EXECUTION_SPEED;
+        p.StateMask   = 0;
+
+        if (!SetThreadInformation(GetCurrentThread(), ThreadPowerThrottling, &p, sizeof(p))) {
+            fprintf(stderr, "warn: failed to disable thread power throttling %d : (%d)\n", prio, (int) GetLastError());
+            return false;
+	}
+    }
+
     if (prio == GGML_SCHED_PRIO_NORMAL) {
         // Keep inherited policy/priority
         return true;
@@ -2450,6 +2468,8 @@ static bool ggml_thread_apply_priority(int32_t prio) {
     struct sched_param p;
     int32_t policy = SCHED_OTHER;
     switch (prio) {
+	// TODO: there seems to be no way to set lower prio on Apple platforms
+        case GGML_SCHED_PRIO_LOW:      policy = SCHED_OTHER; p.sched_priority = 0;  break;
         case GGML_SCHED_PRIO_NORMAL:   policy = SCHED_OTHER; p.sched_priority = 0;  break;
         case GGML_SCHED_PRIO_MEDIUM:   policy = SCHED_FIFO;  p.sched_priority = 40; break;
         case GGML_SCHED_PRIO_HIGH:     policy = SCHED_FIFO;  p.sched_priority = 80; break;
@@ -2506,6 +2526,7 @@ static bool ggml_thread_apply_priority(int32_t prio) {
     struct sched_param p;
     int32_t policy = SCHED_OTHER;
     switch (prio) {
+        case GGML_SCHED_PRIO_LOW:      policy = SCHED_BATCH; p.sched_priority = 0;  break;
         case GGML_SCHED_PRIO_NORMAL:   policy = SCHED_OTHER; p.sched_priority = 0;  break;
         case GGML_SCHED_PRIO_MEDIUM:   policy = SCHED_FIFO;  p.sched_priority = 40; break;
         case GGML_SCHED_PRIO_HIGH:     policy = SCHED_FIFO;  p.sched_priority = 80; break;