frank-default-small: swap to nameistoken Quark W8A8 INT8, batch 8192

- Model: nameistoken/Qwen3.6-35B-A3B-Quark-W8A8-INT8 (AMD Quark W8A8,
  vLLM-native expert layout). The Avesed quant emitted malformed Qwen3
  XML tool calls; the Quark model follows the format cleanly.
- max-num-batched-tokens lowered 16384 -> 8192 (user request).
- Chat template: neutral path qwen36-chat_template-tools.jinja (same
  base template; adds a concrete worked tool-call example).

scripts/serve-frank-small.sh

@@ -21,14 +21,14 @@ fi
 
 # --- defaults (used when the env file does not set them) -------------------
 : "${VLLM_BIN:=/home/dank/vllm-venv/bin/vllm}"
-: "${MODEL:=Avesed/Qwen3.6-35B-A3B-INT8-W8A8}"
+: "${MODEL:=nameistoken/Qwen3.6-35B-A3B-Quark-W8A8-INT8}"
 : "${ALIAS:=frank-default-small}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=52625}"
 : "${MAX_MODEL_LEN:=262144}"
 : "${KV_CACHE_DTYPE:=auto}"
 : "${MAX_NUM_SEQS:=4}"
-: "${MAX_NUM_BATCHED_TOKENS:=16384}"
+: "${MAX_NUM_BATCHED_TOKENS:=8192}"
 : "${GPU_MEMORY_UTILIZATION:=0.92}"
 : "${NGRAM_LOOKUP_MAX:=5}"
 : "${NGRAM_LOOKUP_MIN:=1}"
@@ -38,7 +38,7 @@ fi
 # The Avesed tokenizer_config.json has no chat_template; vLLM would use its
 # built-in template which does not render the model's XML tool format. Use
 # the repo's chat_template.jinja (ships the <tool_call> instructions).
-: "${CHAT_TEMPLATE:=/home/dank/models/avesed-qwen36-chat_template.jinja}"
+: "${CHAT_TEMPLATE:=/home/dank/models/qwen36-chat_template-tools.jinja}"
 
 if [[ ! -x "$VLLM_BIN" ]]; then
     echo "missing vllm binary: $VLLM_BIN" >&2