diff --git a/recipes/glm-5-3-flash-max-effort-on-2x-cmp170hx-exl3-tp2-four-slots/recipe.yaml b/recipes/glm-5-3-flash-max-effort-on-2x-cmp170hx-exl3-tp2-four-slots/recipe.yaml
index a05d0aa17..0b2f1599d 100644
--- a/recipes/glm-5-3-flash-max-effort-on-2x-cmp170hx-exl3-tp2-four-slots/recipe.yaml
+++ b/recipes/glm-5-3-flash-max-effort-on-2x-cmp170hx-exl3-tp2-four-slots/recipe.yaml
@@ -4,9 +4,9 @@ engine:
   name: exllamav3
   source_type: fork
   git_url: 'https://github.com/alexvnesta/glm53-flash-cmp170hx-tp'
-  pinned_commit: fa0adf1899015f692ddce30391ee7e740a0910c9
-  install_note: '[base_version 0f685aa + row32 four-slot profile] Source build required; no image. Follow https://github.com/alexvnesta/glm53-flash-cmp170hx-tp/blob/fa0adf1899015f692ddce30391ee7e740a0910c9/profiles/community-four-active/README.md. Set up the pinned venv; apply_engine.sh; install gguf==0.17.1; profiles/community-four-active/build.sh /ABS/profile; get_models.sh using the prepared engine/native directories; obtain the gated GLP44 vector under your own account; launch run.sh with GLM53_COMMUNITY_PROFILE and GLM_WEIGHTLESS_VECTOR. Rebuilt extension hashes vary with build paths. Two 64 GiB cards, CUDA 13.3, Python 3.13 and the pinned Torch environment were used.'
-summary: 'Four native active sequences on two 64 GiB CMP170HX cards; GLM-5.3-Flash EXL3 3.05bpw, TP2, with the Weightless GLP44 steering vector at alpha 2, FP16 recurrent state, Q8 GPU KV, DFlash2 K7 and hybrid15. This recipe records max reasoning effort, selected per request with model GLM-5.3-Flash-max. llm-inference-bench v0.8.0, unmodified under a per-agent counting wrapper, measures 1, 2 and 4 agents on short and nominal 32K/128K inputs, one 30-second run per cell; actual tokenized input lengths are recorded. Native completion-token usage includes reasoning. Active RAM KV paging is disabled. The 655,360-token pool is shared, with 392,960 including output as the per-request cap. Throughput is inference speed, not an accuracy or intelligence score. Differences between the low, high and max recipes are not separated from run-to-run variation, and with ignore-EOS effort changes what the model writes, not how many tokens.'
+  pinned_commit: db01c256a8003daf90c932ee25552526ede40f1f
+  install_note: '[base_version 0f685aa + row32 four-slot profile] Source build required; no image. Follow https://github.com/alexvnesta/glm53-flash-cmp170hx-tp/blob/db01c256a8003daf90c932ee25552526ede40f1f/profiles/community-four-active/README.md. Set up the pinned venv; apply_engine.sh; install gguf==0.17.1; profiles/community-four-active/build.sh /ABS/profile; get_models.sh using the prepared engine/native directories; obtain the gated GLP44 vector under your own account; launch run.sh with GLM53_COMMUNITY_PROFILE and GLM_WEIGHTLESS_VECTOR. Rebuilt extension hashes vary with build paths. Two 64 GiB cards, CUDA 13.3, Python 3.13 and the pinned Torch environment were used.'
+summary: 'Four native active sequences on two 64 GiB CMP170HX cards; GLM-5.3-Flash EXL3 3.05bpw, TP2, with the Weightless GLP44 steering vector at alpha 2, FP16 recurrent state, Q8 GPU KV, DFlash2 K7 and hybrid15. This recipe records max reasoning effort, selected per request with model GLM-5.3-Flash-max. llm-inference-bench v0.8.0, unmodified under a per-agent counting wrapper, measures 1, 2 and 4 agents on short and nominal 32K/128K inputs, one 30-second run per cell; actual tokenized input lengths are recorded. Native completion-token usage includes reasoning. Active RAM KV paging is disabled. The 655,360-token pool is shared, with 392,960 including output as the per-request cap. Throughput is inference speed, not an accuracy or intelligence score. Differences between the low, high and max recipes are not separated from run-to-run variation, and with ignore-EOS effort changes what the model writes, not how many tokens. Accepts optional chat_template_kwargs.clear_thinking (default-off).'
 license: CC-BY-4.0
 model:
   name: GLM-5.3-Flash-EXL3-3.05bpw
@@ -33,7 +33,7 @@ config:
   launch:
     - ./profiles/community-four-active/run.sh
   active_kv: 'GPU-resident Q8 pool 655360 shared tokens, 392960 cap including output per request; no active RAM paging'
-  report_url: 'https://github.com/alexvnesta/glm53-flash-cmp170hx-tp/blob/fa0adf1899015f692ddce30391ee7e740a0910c9/docs/COMMUNITY_BENCHMARK_2026-10-17.md'
+  report_url: 'https://github.com/alexvnesta/glm53-flash-cmp170hx-tp/blob/db01c256a8003daf90c932ee25552526ede40f1f/docs/COMMUNITY_BENCHMARK_2026-10-17.md'
   weightless:
     alpha: 2
     layers: 1-44