Edition of Tuesday 10 November 2026

I ran 120B MoE models on my 32GB M1 Max using under 16 GB

Comments on “I ran 120B MoE models on my 32GB M1 Max using under 16 GB”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

A developer ran 120-billion-parameter mixture-of-experts models on a 32GB M1 Max by keeping most expert weights on SSD under a 16 GiB process-memory budget. Their engine averaged 7.84 tokens/s versus 5.78 for TUFF 10.2.2 on matched BF16 weights, and degraded less when another process used memory.

Read the original at mitln.github.io. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 72 of 95 with a score of 0.58. The panel rated it highest on technical depth (0.82) and new information (0.82), lowest on audience breadth (0.44). The judges disagreed most on substantiated (spread 0.41), so the story is marked contested. Placed No. 72, No. 68 by score alone: the 25th AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Detailed, well-caveated engineering experiment on local MoE inference on Apple Silicon with benchmarks against a baseline; narrow audience and single-machine, unreplicated results limit breadth and significance.
AI judgeJudge 3gpt-5.6-luna
Detailed, reproducible local-inference benchmarks and correctness checks show a meaningful engineering result for Apple Silicon and MoE users, while clearly acknowledging single-machine limits and the unreleased prototype.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.58total under rubric v2.3Contestedjudges differ by 0.41 on substantiated

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.48
  • Reader interest0.73
  • Audience breadth0.44
  • Practical relevance0.63
  • Substantiated0.76
  • Technical depth0.82
  • New information0.82
  • Counts against: Promotional0.08
  • Counts against: Overclaim0.24

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.480.350.620.480.27+0.24+0.116
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.690.600.900.730.30+0.26+0.190
Audience breadthHow many people who build technology does it concern?0.450.400.470.440.07+0.13+0.057
Practical relevanceHow useful is it to someone who builds software or tech products?0.620.550.720.630.17+0.22+0.139
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.910.500.880.760.41 , above the contested threshold+0.05+0.038
Technical depthHow technically substantive is it?0.950.700.820.820.25+0.05+0.041
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.890.600.980.820.38+0.05+0.041
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.060.100.080.080.04−0.19−0.015
OverclaimDo the headline or conclusions claim more than the body supports?0.300.350.060.240.29−0.11−0.026
Sum of contributions+0.581
Claim-check penalty0.000
Total, as published0.581

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #72 on Rubric, 10 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-10/72/"><img src="https://rubric.hrih.si/badge/2026-11-10/72.svg" alt="Ranked #72 on Rubric, 10 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 24 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 10 Nov 2026, 05:47 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “I ran 120B MoE models on my 32GB M1 Max using under 16 GB”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.