Add recommended sampling defaults and reduce MoE GPU offload on dankserver

- frank-default-large: add TEMP=1.0, TOP_K=20, TOP_P=0.95, MIN_P=0.0
  (per HauhauCS Qwen3.6-27B model card, thinking-general mode)
- frank-default-small: add same sampling defaults
  (per HauhauCS Qwen3.6-35B-A3B model card)
- frank-default-small: reduce N_CPU_MOE from 33 to 34 (6 expert
  layers on GPU instead of 7) to prevent OOM during high-load sessions
- Both serve scripts pass --temp, --top-k, --top-p, --min-p to
  llama-server; clients can still override per-request via API

scripts/frank-default-large.env

@@ -33,5 +33,12 @@ CACHE_TYPE_V=q8_0
 # User-specified ubatch 4096 / batch 12288 is not feasible here (see bench).
 BATCH_SIZE=2048
 UBATCH_SIZE=512
+# Sampling settings — per HauhauCS Qwen3.6-27B model card.
+# Thinking-general: temp=1.0, top_p=0.95, top_k=20, min_p=0.
+# Clients may override per-request; these are the server-side defaults.
+TEMP=1.0
+TOP_K=20
+TOP_P=0.95
+MIN_P=0.0
 THREADS=12
 THREADS_HTTP=1