diff --git a/recipes/ds4-flash-3x170hx-pp3-dspark-k5/recipe.yaml b/recipes/ds4-flash-3x170hx-pp3-dspark-k5/recipe.yaml
index c34b1db1e..02d56ece2 100644
--- a/recipes/ds4-flash-3x170hx-pp3-dspark-k5/recipe.yaml
+++ b/recipes/ds4-flash-3x170hx-pp3-dspark-k5/recipe.yaml
@@ -67,11 +67,22 @@ config:
     notes: 'DSpark block size MUST be exactly 5 for this checkpoint (block-5 Markov head); 7 measured acceptance 0% and token salad. max_num_batched_tokens 2048 is pinned by VRAM (~40 MiB free at util 0.98); 4096 OOMs rank1 and was slower before dying. Swap must be disallowed (cgroup v2: equal --memory/--memory-swap); 7.6 GB of paged-out PP worker stalls every stage behind it. CPU pinning matters: unpinned PP workers competing with other host jobs measurably reduce throughput.'
 performance:
   claimed_by: submitter
-  metrics:
-    tok_s: 181
-    context_len: 262144
-    prefill_tok_s: 2350
-    notes: 'T1 self-measured: 181 tok/s structured at 99% accept (33 ms/cycle), 76 tok/s prose at 30%, ceiling 183. Prefill 2,350 tok/s at 2048 batched tokens.'
+  tok_s: 181
+  prefill_tok_s: 2350
+  context_len: 262144
+  notes: 'T1 self-measured: 181 tok/s structured at 99% accept (33 ms/cycle), 76 tok/s prose at 30%, ceiling 183. Prefill 2,350 tok/s at 2048 batched tokens.'
+  points:
+    -
+      context_len: 262144
+      concurrency: 1
+      prefill_tok_s: 2350
+      decode_tok_s: 181
+      notes: 'T1 self-measured: 181 tok/s structured decode at 99% accept (33 ms/cycle), 76 tok/s prose at 30%, ceiling 183; prefill 2,350 tok/s at 2048 batched tokens'
+    -
+      context_len: 131072
+      concurrency: 1
+      decode_tok_s: 78.8
+      notes: 'allover326/deepseek-v4-cmp170hx RESULTS.md @ 3dd2d88, section "3 cards + the INT4 repack: 512k verified" -> "The 3-card run, in full": 3x CMP 170HX, PP3, DSpark num_speculative_tokens 5, --max-model-len 131072, decode ~78.8 tok/s median. The author run used the INT4 repack, layer partition 15,15,13, DSV4_LOGITS_ROW_CHUNK 256, util 0.95; this recipe is the FP8 abliterated checkpoint at 262144 ctx, partition 15,16,12, row chunk 64, util 0.98.'
 artifacts:
   -
     kind: model_weights