Offload one more MoE expert to CPU on frank-default-small (34→35 of 40)

- N_CPU_MOE 34→35: 5 expert layers on GPU instead of 6. Frees ~0.4-0.8 GiB
  VRAM for OOM safety after high-load sessions OOM'd at 32 and 33.
- Sync stale doc references (deployment.md, Dankserver System Specs.md)
  that still claimed 32/8; specs now estimate ~1.8 GiB headroom at 35.

scripts/frank-default-small.env

@@ -8,15 +8,15 @@ PORT=7770
 # (Increased from 3×200k to add a 4th parallel stream.)
 CTX_SIZE=800000
 PARALLEL=4
-# Spec: ngram-mod. n_min=48, n_max=64, n_match=24 (defaults). 6 expert
-# layers back on GPU; 34 on CPU. Batch 8192 / ubatch 2048.
+# Spec: ngram-mod. n_min=48, n_max=64, n_match=24 (defaults). 5 expert
+# layers back on GPU; 35 on CPU. Batch 8192 / ubatch 2048.
 SPEC_TYPE=ngram-mod
 NGRAM_MOD_N_MIN=48
 NGRAM_MOD_N_MAX=64
 NGRAM_MOD_N_MATCH=24
-# Expert offload: 34 of 40 layers keep MoE weights on CPU; remaining
-# 6 layers have their expert weights resident on GPU for faster routing.
-N_CPU_MOE=34
+# Expert offload: 35 of 40 layers keep MoE weights on CPU; remaining
+# 5 layers have their expert weights resident on GPU for faster routing.
+N_CPU_MOE=35
 N_GPU_LAYERS=all
 # KV cache on GPU, K quantized to q8_0, V stays f16 (user-locked decision).
 CACHE_TYPE_K=q8_0

scripts/serve-llama-frank-small.sh

@@ -32,7 +32,7 @@ fi
 : "${NGRAM_MOD_N_MATCH:=24}"
 : "${CACHE_TYPE_K:=q8_0}"
 : "${CACHE_TYPE_V:=f16}"
-: "${N_CPU_MOE:=34}"     # 34 of 40 layers: MoE expert weights stay on CPU; 6 on GPU
+: "${N_CPU_MOE:=35}"     # 35 of 40 layers: MoE expert weights stay on CPU; 5 on GPU
 : "${N_GPU_LAYERS:=all}" # every non-expert tensor goes to GPU
 : "${BATCH_SIZE:=2048}"
 : "${UBATCH_SIZE:=512}"