# Tunables for frank-default-npu (FastFlowLM NPU endpoint, Dankclaw)
# Runtime: FLM 1.0.1 on the XDNA2 NPU (50 TOPS). Model: Gemma4-E4B-IT
# (8B, Q4_1, vision + audio + reasoning). The NPU allocates from the
# unified pool shared with frank-default-large (the CIRU llama.cpp
# service on the iGPU). See serverAppConfigs-docs/FastFlowLM NPU Inference.md.
#
# 2026-08-20: gemma4-it:e4b deployed. Footprint ~9.1 GB. 64k context.

FLM_MODEL=gemma4-it:e4b
FLM_HOST=0.0.0.0
FLM_PORT=52626
FLM_PMODE=performance
FLM_ASR=0
# 64K context (native max for gemma4-it is 32768, but NPU supports up to 256k).
# The model's max_prefill_len is 4096, so prompts longer than that get
# truncated at prefill time.
FLM_CTX_LEN=65536