frank-default-small: pmode turbo, ASR (Whisper-V3-Turbo) on, ctx-len 131072 (max verified)

scripts/frank-default-small.env

@@ -15,4 +15,13 @@
 FLM_MODEL=gemma4-it:e4b
 FLM_HOST=0.0.0.0
 FLM_PORT=52625
-FLM_PMODE=performance
+# Power mode: turbo. Measured decode is bandwidth-bound (turbo ~= performance
+# for this model), but the user requested turbo; it may help prefill.
+FLM_PMODE=turbo
+# Load the ASR model (Whisper-V3-Turbo-NPU2) alongside Gemma4. Exposes
+# /v1/audio/transcriptions. Adds ~1 GiB to the resident footprint.
+FLM_ASR=1
+# Maximum context length. Gemma4 natively supports 128K; the NPU budget
+# (~15 GiB minus the 9.1 GiB footprint) fits 131072. Verified 2026-08-16:
+# loads, KV cache allocates to ~115k, decode ~12 t/s, 13 GiB headroom.
+FLM_CTX_LEN=131072

scripts/serve-flm-small.sh

@@ -28,13 +28,25 @@ fi
 : "${FLM_HOST:=0.0.0.0}"
 : "${FLM_PORT:=52625}"
 : "${FLM_PMODE:=performance}"
+: "${FLM_ASR:=0}"
+: "${FLM_CTX_LEN:=-1}"
 
 if [[ ! -x "$FLM_BIN" ]]; then
     echo "missing flm binary: $FLM_BIN" >&2
     exit 1
 fi
 
+# --- optional flags ----------------------------------------------------------
+OPT_ARGS=()
+if [[ "${FLM_ASR}" != "0" ]]; then
+    OPT_ARGS+=(-a "${FLM_ASR}")
+fi
+if [[ "${FLM_CTX_LEN}" != "-1" ]]; then
+    OPT_ARGS+=(-c "${FLM_CTX_LEN}")
+fi
+
 exec "$FLM_BIN" serve "$FLM_MODEL" \
     --host "$FLM_HOST" \
     -p "$FLM_PORT" \
-    --pmode "$FLM_PMODE"
+    --pmode "$FLM_PMODE" \
+    "${OPT_ARGS[@]}"