# ==============================================================================
# Gemma 4 E4B-it Q4_K_M — bigctx variant (KV in RAM via -nkvo)
# Benchmarked 2026-05-06 v4 (TurboQuant FORCE_MMQ): turbo2 rec ctx=163840
# +139264 tokens vs pure-GPU 24576. turbo2 KV = 2.1 KB/tok vs q4_0 4.5 KB/tok.
# Speed at ctx=163840: baseline 30.0 t/s, est. 17.8@50% / 22.4@25% (PCIe BW).
# RAM at 163840: 346 MiB KV. ngl=42 (all layers on GPU).
# Use this profile when you need >24K context; otherwise use gemma4-e4b.
# ==============================================================================

MODEL_FILE=google_gemma-4-E4B-it-Q4_K_M.gguf

N_GPU_LAYERS=42
CTX_SIZE=163840

THREADS=6
THREADS_BATCH=6

BATCH_SIZE=512
UBATCH_SIZE=128

CACHE_TYPE_K=turbo2
CACHE_TYPE_V=turbo2

PARALLEL=1

EXTRA_ARGS=--flash-attn on --mmap --no-kv-offload