This is the short public index for the week of August 17–23. The detailed posts remain the source of truth. This page is a rollup of already-published measurements and decisions. It does not add a new benchmark run.
New pages dated this week, plus two living updates.
Anchored 0731 ablit @ a1e69379. Same Anemll 1M/6.
oQ2.5e 16k PP, stock config, zero local patches.
Tap StackChan, get Milo. Same brain as Reachy.
| Date | Lane | What | Call |
|---|---|---|---|
| August 17 | Fleet | oMLX dual-ANE on three Macs | PR #2935 fused path is not a speed win on the M5. Current main 821.4 tok/s. |
| August 19 | Fleet | Ornith 1.5-397B Q6_K | Native 262k serve. Cold 246k prefill in 33.8 min at 122 tok/s. Decode 29.7. |
| August 19 | Shop | Don't rsync 400 GB to a Synology | 46 GB cp write held 170 MB/s from Forge and the M4. Reads 17–26 MB/s. |
| August 20 | Fleet | Ornith vs GLM-5.2 | Keep Ornith. GLM IQ3_S tools-pass; decode ~half; 32k prefill DNF in 400 s. 5.3 weights not out. |
| August 20–21 | Robots | Local Hermes · R5a face · talking StackChan | Spare unit recovered, custom face qualified, then tap-to-talk with the same Milo brain. |
| August 21 | Software | Hermes usage pane | 30-day milo profile: 153.3M subscription / 8.2M API / 0.4M local. Public MIT plugin. |
| August 22 | Fleet | Mia 489af95 pin | Recipe upgrade, not a speed win. Tony count 91.6 → 90.7 t/s. Promoted for fail-closed hotfixes. |
| August 22 | Shop | Inference box CAD | Design only. 2×2 Sparks, 40 mm gaps, vented shelves, printed retainers. Fan considered and dropped. |
| August 23 | Fleet | Keys-anchored 0731 ablit | Same Anemll 1M/6. New weights. Tony overnight 78→88 not applied — Funland already ~91 t/s. |
| August 23 | Fleet | oMLX #3059 r1 · r2 stock confirm | Out of the box ANE compiled and did not run. After the chunking fix: +7.1% / +7.0% PP on oQ2.5e, stock. |
| Claim | Number | Source |
|---|---|---|
| oQ2.5e hybrid PP, 16k, stock | 642.1 vs 599.4 tok/s (+7.1%) | Round 2 |
| oMLX current main on M5 | 821.4 tok/s | Three Macs |
| Ornith decode / 32k prefill | 32–35 t/s · 100 s | A/B |
| GLM-5.2 IQ3_S decode / 32k | 17–18 t/s · DNF @ 400 s | same |
| Ornith 246k cold prefill | 2,026 s · 121.6 tok/s · 310 GiB RSS | Ornith 1.5 |
| Mia pin vs Aug 13 | 90.7 vs 91.6 t/s (−0.9%) | Mia Aug 22 |
| NAS 46 GB write / read | 170 MB/s write · 17–26 MB/s read | cp note |
| Hermes 30-day billing split | 153.3M sub · 8.2M API · 0.4M local | Usage pane |
Do not mix these rows into one ranking. Different hosts, engines, prompt lengths, and jobs.
The Bambu H2C arrived early (original ETA August 25). Sunday it finished first calibration, AMS 2 Pro #1, and a built-in Benchy on Soleyin matte grey PLA. Hull, overhangs, bridges, and chimney were clean; leftover stringing is cosmetic. Next prints are a purge bin, then Gridfinity, then the Spark-rack retainers from the inference-box model.
The living NAS page was updated August 20: RAID-6 Healthy, local backup tier still not 3-2-1. Reachy Mini remains the original physical avatar; StackChan is the second body, not a second brain.
The useful pattern is the same one as last month: pin recipes for fail-closed reasons, measure speed separately, and do not promote a patch because a tweet has a round number. StackChan earned a conversation post only after local control and a custom face were already proven. The usage plugin exists because the table was already there — the missing piece was a page.