docs: measured throughput + memory footprint

README.md

@@ -69,9 +69,23 @@ with a residual gap to the 7B's exactness on L0 (the next lever is on-policy dis
 
 The stages this model serves are **prefill-bound with short outputs** — the regime where shrinking
 the model (not speculative decoding) is the right lever. In the UltraCode daemon it loads into a
-dedicated `.enrich` worker (~0.9 GB VRAM, Q8_0 + KV) that co-resides with the main LLM, so the
-label stages run on the 0.6B while paragraph/prose stages stay on the larger model. Measured prefill
-throughput on the label batches: ~8–12k tok/s.
+dedicated `.enrich` worker that co-resides with the main LLM, so label stages run on the 0.6B while
+paragraph/prose stages stay on the larger model.
+
+Measured on a laptop RTX 5060 (8 GB), llama.cpp CUDA, Q8_0, `n_ctx=8192`, `n_batch=2048`:
+
+| What | Rate |
+|---|---|
+| Prefill, 850-token label prompt | **~17 000 tok/s** |
+| Decode, single stream | **301 tok/s** |
+| Label stage end-to-end, batched (prompt + generated) | **~2 600 tok/s** |
+
+The end-to-end figure is the one to plan capacity with: label prompts are short and the stage runs
+many of them concurrently, so wall-clock is dominated by prefill, not by decode.
+
+**Memory:** 604 MiB of weights, but **~2.7 GB resident** at `n_ctx=8192` once the KV cache and
+compute buffers are allocated. Size the deployment from that number, not from the file. A smaller
+`n_ctx` reduces it proportionally — 8192 is chosen here to keep eight label sequences in flight.
 
 ## Usage (llama.cpp)