card: publish both serving configs with measured quality/speed tradeoff

README.md

@@ -27,10 +27,22 @@ important difference: **this model's calibration holds out all 92 eval items**
 the reference's own grader (`ds4-eval --regrade-trace`, self-check 92/92) at the
 matched thinking budget, serving on dflash with fused decode off.
 
-## Speed (measured, Radeon 8060S iGPU, 128 GB)
-
-- **18.1 tok/s** median decode (plain autoregressive, no draft), 1200-token
-  generations, coherent long-form output; prefill ~1.1 s on short prompts.
+## Serving configs (measured, Radeon 8060S iGPU, 128 GB)
+
+Two supported configurations — pick per workload. The speed lever is
+`--ds4-expert-top-k 4` (4 instead of the model-default 6 routed experts per
+token) plus fused decode; it costs measured quality, stated below, never
+hidden:
+
+| config | flags | decode | COMPSEC-17 |
+|---|---|---|---|
+| **quality** (default) | model-default top-k 6, fused decode off | 18.1 tok/s | **17/17** |
+| **throughput** | `--ds4-expert-top-k 4 --ds4-fused-decode` | **22.3 tok/s** (+23%) | 16/17 |
+
+The 82/92 full-eval score was measured at the quality config. The DSpark
+speculative drafter does NOT currently help this artifact (accept rate
+0.51–0.67 vs 0.837 on the reference it was calibrated for — net slower);
+draft–target co-calibration for mix-quantized targets is an open item.
 
 ## Bit allocation