diff --git a/stacks/llama-swap/config.yaml b/stacks/llama-swap/config.yaml
index c3888bd..4aa1254 100644
--- a/stacks/llama-swap/config.yaml
+++ b/stacks/llama-swap/config.yaml
@@ -27,6 +27,12 @@
 #   2026-04-22: New `pinned` group — qwen3.5-9b + qwen3.6-35-a3b coexist
 #               in VRAM with persistent=true and ttl=0. Means the two
 #               can be called concurrently and never idle-unload.
+#   2026-04-26: Added qwen3.6-35-a3b-heretic (llmfan46 uncensored heretic
+#               Q6_K, ~28GB) and qwen3.6-27b (unsloth dynamic UD-Q6_K_XL,
+#               ~26GB). Both pre-pulled into /tank/aimodels/huggingface
+#               via huggingface_hub.snapshot_download with hf_transfer.
+#               Both repos include mmproj-BF16.gguf — llama-server's -hf
+#               flag auto-loads it, so vision works without --mmproj.
 # ============================================================================
 
 # Default 1200 seconds (20 min) to wait for model to be available to load.
@@ -164,6 +170,50 @@ models:
       --reasoning on
       --reasoning-format deepseek
 
+  "qwen3.6-35-a3b-heretic":
+    name: "Qwen 3.6 35B-A3B Uncensored Heretic Q6_K (vision)"
+    description: "Qwen3.6 MoE, 3B active of 35B. llmfan46 uncensored 'heretic' Q6_K (~28GB) + auto-loaded BF16 mmproj for vision."
+    ttl: 600
+    cmd: |
+      /app/llama-server
+      --context-shift
+      --jinja
+      -hf llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF:Q6_K
+      --port ${PORT}
+      --n-gpu-layers 999
+      --ctx-size 131072
+      --flash-attn on
+      --temp 1.0
+      --top-p 0.95
+      --top-k 20
+      --min-p 0.00
+      --presence-penalty 1.5
+      --repeat-penalty 1.0
+      --reasoning on
+      --reasoning-format deepseek
+
+  "qwen3.6-27b":
+    name: "Qwen 3.6 27B UD-Q6_K_XL (vision)"
+    description: "Qwen3.6 dense 27B. Unsloth dynamic Q6_K_XL (~26GB) + auto-loaded BF16 mmproj for vision."
+    ttl: 600
+    cmd: |
+      /app/llama-server
+      --context-shift
+      --jinja
+      -hf unsloth/Qwen3.6-27B-GGUF:UD-Q6_K_XL
+      --port ${PORT}
+      --n-gpu-layers 999
+      --ctx-size 131072
+      --flash-attn on
+      --temp 1.0
+      --top-p 0.95
+      --top-k 20
+      --min-p 0.00
+      --presence-penalty 1.5
+      --repeat-penalty 1.0
+      --reasoning on
+      --reasoning-format deepseek
+
   # ==========================================================================
   # NEMOTRON MODELS (KB-recommended settings)
   # - General Chat: temp 1.0, top-p 1.0, min_p 0.01