Switch frank-default-small to Ornith Q6_K

scripts/serve-frank-small.sh

@@ -1,16 +1,14 @@
 #!/usr/bin/env bash
-# Serve dealignai/Ornith-1.5-35B-A3B-UNCENSORED (CRACK, Q8_0) as
+# Serve dealignai/Ornith-1.5-35B-A3B-UNCENSORED (CRACK, Q6_K) as
 # frank-default-small via upstream llama.cpp on Dankserver (RTX 3090, MoE
 # experts on CPU).
 #
 # Runtime: upstream llama.cpp llama-server (b10121). The model is a 35B-total /
 # 3B-active MoE-dense hybrid with the MTP speculative head bundled in the GGUF.
 #
-# Expert offload: instead of the layer-counter --n-cpu-moe, the expert (FFN
-# exps) tensors are pinned to CPU explicitly with --override-tensor. The
-# pattern is the internal MoE exps regex (the same one --n-cpu-moe expands),
-# so only the Mixture-of-Experts weight tensors move to CPU; every other
-# tensor stays on the GPU up to --gpu-layers.
+# Expert offload: the expert (FFN exps) tensors selected by the layer-bounded
+# --override-tensor pattern are pinned to CPU. The final output-adjacent
+# blocks stay on CUDA with all non-expert tensors, including the MTP head.
 #
 # Spec: MoE model with a bundled MTP head -> native draft-mtp (the head is
 # auto-detected from the target model; b10121 creates the MTP draft context
@@ -32,7 +30,7 @@ fi
 
 # --- defaults (used when the env file does not set them) -----------------
 : "${MODEL_DIR:=/home/dank/models}"
-: "${MODEL_FILE:=Ornith-1.5-35B-A3B-CRACK-Q8_0.gguf}"
+: "${MODEL_FILE:=Ornith-1.5-35B-A3B-CRACK-Q6_K.gguf}"
 : "${MMPROJ_FILE:=mmproj-Ornith-1.5-35B-A3B-f16.gguf}"
 : "${LLAMA_SERVER:=/home/dank/llama.cpp/build/bin/llama-server}"
 : "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"