frank-small: record measured cutover values; unit Description follows the Swift swap

Boot ledger lines, 19,404 used / 4,721 MiB free (the q8_0 proof), decode arms (66.1 t/s @0.8, 66.9 @0, 58.9 @recipe 1.0 with acceptance 52.1%/52.2%/44.8%), vision Red probe, reasoning_effort xhigh/high contract, e2e 12-crawl transient + full-gate green rerun. Unit Description updated in-repo; the relinked unit picks it up at the next deploy/restart (no bounce for cosmetics). 360/360 suite green.

scripts/frank-small.service

@@ -1,5 +1,5 @@
 [Unit]
-Description=llama.cpp MiMo-V2.6-Distill-Qwen-9B Q6_K GGUF (qwen35 hybrid, 2x200704, unquantized f16 KV, mmproj vision) on the RTX 3090 (dankclaw, frank-small)
+Description=llama.cpp Swift-1.5-Qwen3.8-27B GSQ-RCO IQ3_S-mtp GGUF (qwen35 hybrid, 1x131072, q8_0 K+V, in-file MTP head, mmproj vision) on the RTX 3090 (dankclaw, frank-small)
 After=network-online.target
 Wants=network-online.target
 

scripts/stack-qwen38-official-fp8.py

@@ -230,6 +230,7 @@ def fill_ple_shard(job):
                                       count=(r1 - r0) * cols,
                                       offset=src_off + r0 * cols)
                 q = lut.take(codes)
+                del codes  # release the mmap export before sm.close()
                 q[~np.isfinite(q)] = 0.0
                 q *= np.float32(scale_f32)
                 packed = f32_to_bf16_rne(q)
@@ -525,6 +526,7 @@ def verify(stage, prefixes, n_e, shapes, meta, shard_ids, rows, hd,
                 codes = np.frombuffer(mm, dtype=np.uint8, count=hd,
                                       offset=off + r * hd)
                 q = lut.take(codes) * np.float32(scale_f32)
+                del codes  # release the mmap export before mm.close()
                 want = f32_to_bf16_rne(q).tobytes()
                 got_row = sum(rows[:i]) + r
                 with open(out_path, "rb") as ofh: