diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env
index b8b6ca7..c4b869e 100644
--- a/scripts/frank-default-large.env
+++ b/scripts/frank-default-large.env
@@ -20,19 +20,11 @@ SPEC_NGRAM_MOD_N_MATCH=24
 DEVICE=ROCm0
 # Dense model (Qwen3.6-27B, not MoE): no MoE CPU offload. Full offload.
 N_GPU_LAYERS=all
-# KV on GPU, quantized (K q8_0, V q8_0). V MUST match K: this llama.cpp
-# build has GGML_CUDA_FA_ALL_QUANTS=OFF, and Flash Attention requires
-# K type == V type. Mixed q8_0/f16 silently disables FA, collapsing
-# long-context decode to ~1 t/s at 200k ctx. q8_0 V halves V memory too.
-CACHE_TYPE_K=q8_0
-CACHE_TYPE_V=q8_0
-# Batch sizing constrained by ROCm memory at 602100 ctx (3x200700):
-# KV ~50GB + model 29.77GB leave only ~16GB for compute graphs. The compute
-# graph scales with UBATCH, so ubatch must stay ~512; ubatch 2048 OOMs even
-# at batch 2048. Proven-fits config: batch 2048 / ubatch 512.
-# User-specified ubatch 4096 / batch 12288 is not feasible here (see bench).
-BATCH_SIZE=2048
-UBATCH_SIZE=512
+# KV on GPU, fp16 (unquantized). Default ggml_type for both K and V.
+# Batch sizing: fp16 KV is larger than q8_0, but user has verified this
+# configuration fits. See frank-default-large-benchmark.md.
+BATCH_SIZE=8192
+UBATCH_SIZE=2048
 # Sampling settings — per HauhauCS Qwen3.6-27B model card.
 # Thinking-general: temp=1.0, top_p=0.95, top_k=20, min_p=0.
 # Clients may override per-request; these are the server-side defaults.
diff --git a/scripts/serve-llama-frank-large.sh b/scripts/serve-llama-frank-large.sh
index 30e4b20..c088350 100755
--- a/scripts/serve-llama-frank-large.sh
+++ b/scripts/serve-llama-frank-large.sh
@@ -33,10 +33,8 @@ fi
 : "${SPEC_NGRAM_MOD_N_MATCH:=24}"
 : "${DEVICE:=ROCm0}"
 : "${N_GPU_LAYERS:=all}"
-: "${CACHE_TYPE_K:=q8_0}"
-: "${CACHE_TYPE_V:=q8_0}"
-: "${BATCH_SIZE:=2048}"
-: "${UBATCH_SIZE:=512}"
+: "${BATCH_SIZE:=8192}"
+: "${UBATCH_SIZE:=2048}"
 : "${TEMP:=1.0}"
 : "${TOP_K:=20}"
 : "${TOP_P:=0.95}"
@@ -66,8 +64,6 @@ exec "$LLAMA_SERVER" \
     --device "$DEVICE" \
     --gpu-layers "$N_GPU_LAYERS" \
     --fit off \
-    --cache-type-k "$CACHE_TYPE_K" \
-    --cache-type-v "$CACHE_TYPE_V" \
     --ctx-size "$CTX_SIZE" \
     --parallel "$PARALLEL" \
     --batch-size "$BATCH_SIZE" \