diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml
index 7d6ecf2..2f5e931 100644
--- a/stacks/litellm/conf/config.yaml
+++ b/stacks/litellm/conf/config.yaml
@@ -54,12 +54,12 @@ model_list:
     model_info:
       mode: chat
 
-  # alias: summarizer-large -> gen / qwen3.6-27b-aeon (operator 2026-07-05). For heavier
-  #   summarization that wants the AEON 27B `gen` model instead of granite-8b. Thinking OFF
+  # alias: summarizer-large -> gen / qwen3.6-35b-a3b-heretic (operator 2026-07-05). For heavier
+  #   summarization that wants the 35B-A3B heretic `gen` model instead of granite-8b. Thinking OFF
   #   (matches gen). Keep api_base (:8015) + enable_thinking in sync with the gen record below.
   - model_name: summarizer-large
     litellm_params:
-      model: hosted_vllm/qwen3.6-27b-aeon
+      model: hosted_vllm/qwen3.6-35b-a3b-heretic
       api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       presence_penalty: 1.5
@@ -104,12 +104,12 @@ model_list:
     model_info:
       mode: chat
 
-  # --- Qwen3.6-27B AEON (uncensored/abliterated, NVFP4 ModelOpt, VISION-INTACT image+video)
-  #     — the general / `gen` model on ana-ml2 GPU 0. REPLACED qwopus3.5-122b 2026-07-05
-  #     (operator: displace qwopus, this assumes gen/gen-reasoning). Dense 27B, qwen3_5
-  #     GDN-hybrid (qwopus's little sibling), native MTP head. Served on :8015 via vLLM,
-  #     served-name qwen3.6-27b-aeon, MTP OFF (spec-decode hurts concurrent aggregate — the
-  #     MTP twin is char-rp below). Thinking split = chat_template_kwargs.enable_thinking +
+  # --- Qwen3.6-35B-A3B heretic (llmfan46, uncensored, NVFP4 ModelOpt Experts-Only, VISION-INTACT)
+  #     — the general / `gen` model on ana-ml2 GPU 0, at /tank/aimodels/qwen36-35b-a3b-heretic-nvfp4.
+  #     Displaced AEON-27B 2026-07-08 (which had displaced qwopus3.5-122b 2026-07-05). MoE 35B-A3B
+  #     (256 experts / 8 active), qwen3_5_moe GDN-hybrid, native MTP preserved but served MTP-OFF
+  #     (spec-decode hurts concurrent aggregate). Served on :8015 via vLLM,
+  #     served-name qwen3.6-35b-a3b-heretic. Thinking split = chat_template_kwargs.enable_thinking +
   #     --reasoning-parser qwen3; tool-calling qwen3_coder. gen / gen-reasoning + summarizer-
   #     large route here; -reasoning enables thinking. Keep api_base (:8015) in sync.
   #     RETIRED with the displacement (→ 404, callers migrate to gen): qwen3.5-122-a10b
@@ -121,7 +121,7 @@ model_list:
   #     GENERAL thinking profile, not the 0.6 coding sub-profile). docs/pfi/model-sampler-defaults.md. ---
   - model_name: gen
     litellm_params:
-      model: hosted_vllm/qwen3.6-27b-aeon
+      model: hosted_vllm/qwen3.6-35b-a3b-heretic
       api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       presence_penalty: 1.5
@@ -137,7 +137,7 @@ model_list:
     litellm_params:
       # Distinct served-name so a thinking-off `gen` request can't mutate this deployment's
       # enable_thinking (shared-config-mutation footgun). Same backend :8015, different model id.
-      model: hosted_vllm/qwen3.6-27b-aeon-thinking
+      model: hosted_vllm/qwen3.6-35b-a3b-heretic-thinking
       api_base: http://10.250.50.54:8015/v1
       api_key: os.environ/VLLM_API_KEY
       presence_penalty: 1.5