diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env
index 7980a17..9feaac4 100644
--- a/scripts/frank-default-large.env
+++ b/scripts/frank-default-large.env
@@ -9,8 +9,11 @@
 # HIP runtime reads those bare env vars (see the 2026-08-13 TEMP incident).
 # llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
 
-# ROCmFPX build with TurboQuant KV-cache support.
+# PromptForge ROCmFPX build and its historical ROCm 7.15 SDK environment.
 LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server
+ROCM_DEVEL=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel
+ROCM_LIB=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_libraries
+ROCM_CORE=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_core
 
 # Model files from https://huggingface.co/kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF.
 MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP
@@ -37,13 +40,13 @@ LISTEN_PORT=7770
 CTX_SIZE=262144
 PARALLEL=1
 # Batch/ubatch follow the existing qualified Dankclaw profile.
-BATCH_SIZE=512
-UBATCH_SIZE=512
+BATCH_SIZE=4096
+UBATCH_SIZE=4096
 NUM_THREADS=16
 THREAD_BATCH=32
 CACHE_TYPE_K=f16
-CACHE_TYPE_V=turbo4
-CTX_CHECKPOINTS=32
+CACHE_TYPE_V=f16
+CTX_CHECKPOINTS=16
 CACHE_RAM=8192
 
 # Standalone MTP draft head, loaded from MTP_DRAFT_FILE by the serve script.
diff --git a/scripts/serve-frank-large.sh b/scripts/serve-frank-large.sh
index 2eeb4b5..28fa305 100755
--- a/scripts/serve-frank-large.sh
+++ b/scripts/serve-frank-large.sh
@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # Serve the kingjones Qwen3.8 Uncensored Q6 AGENT model as frank-default-large.
-# The deployment uses a standalone MTP draft head and Turbo4 V-side KV cache.
+# The deployment uses a standalone MTP draft head and f16 KV cache.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
@@ -22,13 +22,13 @@ fi
 : "${LISTEN_PORT:=7770}"
 : "${CTX_SIZE:=262144}"
 : "${PARALLEL:=1}"
-: "${BATCH_SIZE:=2048}"
-: "${UBATCH_SIZE:=512}"
+: "${BATCH_SIZE:=4096}"
+: "${UBATCH_SIZE:=4096}"
 : "${NUM_THREADS:=16}"
 : "${THREAD_BATCH:=32}"
 : "${CACHE_TYPE_K:=f16}"
-: "${CACHE_TYPE_V:=turbo4}"
-: "${CTX_CHECKPOINTS:=32}"
+: "${CACHE_TYPE_V:=f16}"
+: "${CTX_CHECKPOINTS:=16}"
 : "${CACHE_RAM:=8192}"
 : "${MTP_N_MAX:=4}"
 : "${MTP_N_MIN:=0}"
@@ -55,14 +55,18 @@ if [[ ! -x "$LLAMA_BIN" ]]; then
     exit 1
 fi
 SERVER_DIR="$(cd -- "$(dirname -- "$LLAMA_BIN")" && pwd)"
-ROCM_PATH="${ROCM_PATH:-/opt/rocm}"
-LIBRARY_PATH="$SERVER_DIR:$ROCM_PATH/lib:$ROCM_PATH/lib/rocm_sysdeps/lib:$ROCM_PATH/lib/llvm/lib:$ROCM_PATH/llvm/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
+ROCM_PATH="${ROCM_DEVEL:-${ROCM_PATH:-/opt/rocm}}"
+if [[ -n "${ROCM_LIB:-}" && -n "${ROCM_CORE:-}" ]]; then
+    LIBRARY_PATH="$ROCM_LIB/lib:$ROCM_CORE/lib:$ROCM_DEVEL/lib/llvm/lib:$SERVER_DIR:${LD_LIBRARY_PATH:-}"
+else
+    LIBRARY_PATH="$SERVER_DIR:$ROCM_PATH/lib:$ROCM_PATH/lib/rocm_sysdeps/lib:$ROCM_PATH/lib/llvm/lib:$ROCM_PATH/llvm/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
+fi
 
 exec /usr/bin/env \
     ROCM_PATH="$ROCM_PATH" \
     HIP_VISIBLE_DEVICES=0 \
-    HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
     LD_LIBRARY_PATH="$LIBRARY_PATH" \
+    HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
     GGML_CUDA_GRAPH_OPT=0 \
     LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0 \
     LLAMA_MTP_CPU_ARGMAX_FASTPATH=1 \
diff --git a/tests/frank_large_config.bats b/tests/frank_large_config.bats
index fe6a3ba..fbd1c7d 100644
--- a/tests/frank_large_config.bats
+++ b/tests/frank_large_config.bats
@@ -46,15 +46,15 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
     grep -q 'preserve_reasoning":true' "$ENV_FILE"
 }
 
-@test "frank-default-large uses Turbo4 only for the V cache" {
+@test "frank-default-large uses f16 for both KV cache sides" {
     grep -q '^CACHE_TYPE_K=f16$' "$ENV_FILE"
-    grep -q '^CACHE_TYPE_V=turbo4$' "$ENV_FILE"
+    grep -q '^CACHE_TYPE_V=f16$' "$ENV_FILE"
     grep -qF -- '-ctk "$CACHE_TYPE_K" -ctv "$CACHE_TYPE_V"' "$SERVE_FILE"
 }
 
 @test "frank-default-large exposes a swappable ubatch" {
-    grep -q '^UBATCH_SIZE=512$' "$ENV_FILE"
-    grep -q ': "${UBATCH_SIZE:=512}"' "$SERVE_FILE"
+    grep -q '^UBATCH_SIZE=4096$' "$ENV_FILE"
+    grep -q ': "${UBATCH_SIZE:=4096}"' "$SERVE_FILE"
     grep -q -- '-ub "$UBATCH_SIZE"' "$SERVE_FILE"
 }