# frank-secondary — llama.cpp (master, CUDA sm_86) serving
# HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP
# (Q4_K_M) on the RTX 3090, :7771.
#
# 2026-10-07 (Frank): swap from Swift-1.5-Qwen3.8-27B RCO-IQ3_XXS to
# Gemma4-26B-A4B Q4_K_M, ONE 200,704 context, q8_0 KV (FP8 class),
# MTP via separate assistant file (--spec-draft-model).
#
# Architecture: gemma4 MoE — 30 layers, 128 experts (8 active),
# hybrid attention: 25 sliding_window + 5 full_attention
# (full at layers [5, 11, 17, 23, 29]), sliding_window 1024,
# 8 KV heads, head_dim 256, attention_k_eq_v (V = K),
# native 262,144 window.
#
# KV: q8_0 K + q8_0 V (FP8 class, 1.0625 B/elem). The build has no
# true fp8 KV dtype; q8_0 is the FP8 class.
#
# MTP: separate assistant file (mtp-gemma-4-26B-A4B-it.gguf, 0.252 GiB),
# loaded via --spec-draft-model + --spec-type draft-mtp.
LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server
MODEL_FILE=/home/dank/models/Gemma4-26B-A4B/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M.gguf
MMPROJ_FILE=/home/dank/models/Gemma4-26B-A4B/mmproj-Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-BF16.gguf
ALIAS=frank-secondary
BIND_ADDR=0.0.0.0
LISTEN_PORT=7771
CTX_SIZE=200704
PARALLEL=1
BATCH_SIZE=4096
UBATCH_SIZE=2048
CACHE_TYPE_K=q8_0
CACHE_TYPE_V=q8_0
SPEC_TYPE=draft-mtp
SPEC_DRAFT_N_MAX=3
SPEC_DRAFT_FILE=/home/dank/models/Gemma4-26B-A4B/mtp-gemma-4-26B-A4B-it.gguf
NGL=99