Switch frank-default-small to Ornith Q6_K

tests/frank_small_config.bats

@@ -0,0 +1,37 @@
+#!/usr/bin/env bats
+# Seam: frank-default-small model, context, tensor placement, and template.
+# This test covers only the Q6_K deployment contract.
+
+load helpers
+
+ENV_FILE="$REPO_ROOT/scripts/frank-default-small.env"
+SERVE_FILE="$REPO_ROOT/scripts/serve-frank-small.sh"
+UNIT_FILE="$REPO_ROOT/scripts/frank-default-small.service"
+TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
+
+@test "frank-default-small selects the Ornith Q6_K model" {
+    grep -q '^MODEL_FILE=Ornith-1\.5-35B-A3B-CRACK-Q6_K\.gguf$' "$ENV_FILE"
+    grep -q 'Ornith-1\.5-35B-A3B-CRACK-Q6_K\.gguf' "$SERVE_FILE"
+}
+
+@test "frank-default-small uses 196608 context per slot across three slots" {
+    grep -q '^CTX_SIZE=589824$' "$ENV_FILE"
+    grep -q '196608 ctx each' "$ENV_FILE"
+    grep -q '^PARALLEL=3$' "$ENV_FILE"
+}
+
+@test "frank-default-small keeps final four expert blocks on CUDA" {
+    grep -q '^OVERRIDE_EXPERT=' "$ENV_FILE"
+    grep -Fq '35|36)\.ffn_' "$ENV_FILE"
+    grep -q '^OVERRIDE_BUFT=CPU$' "$ENV_FILE"
+    grep -q '^N_GPU_LAYERS=all$' "$ENV_FILE"
+}
+
+@test "frank-default-small uses the tracked Qwen-Sharp template" {
+    grep -q '^CHAT_TEMPLATE_FILE=' "$ENV_FILE"
+    grep -q 'peculiar-ragdoll/Qwen-Sharp-Chat-Templates' "$ENV_FILE"
+    grep -q 'chat-template\.jinja' "$SERVE_FILE"
+    [ -s "$TEMPLATE_FILE" ]
+    grep -q 'qwen3\.8-froggeric-v22\.4\.0' "$TEMPLATE_FILE"
+    grep -q 'Qwen-Sharp' "$UNIT_FILE"
+}