Edition of Friday 13 November 2026

Inkling 2 Small on vLLM: Day-0 Support

Comments on “Inkling 2 Small on vLLM: Day-0 Support”

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

vLLM now supports Thinking Machines' Inkling 2 Small on day 0, a 594B-parameter (17B active) multimodal MoE model with 1M-token context. The release adds a native DSpark speculator, NVFP4/MXFP8 mixed-precision experts that allow single-node serving, and kernel and attention optimizations reaching up to 630 tokens/s per user at TP4, plus…

Read the original at vllm.ai. 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. 137 of 137 with a score of 0.56. The panel rated it highest on new information (0.93) and technical depth (0.93), lowest on audience breadth (0.49). The judges disagreed most on promotional (spread 0.54), so the story is marked contested. Placed No. 137, No. 127 by score alone: the 53rd AI & machine learning story of the day (−0.080), and close to “Inkling-2-Small weights released”, No. 9 today (−0.036). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Detailed technical writeup of a new open-weight multimodal MoE model's architecture and serving optimizations; substantive kernel and benchmark detail, with some promotional framing from the serving vendor and an unverified source for the release.
AI judgeJudge 3gpt-5.6-luna
A technically detailed serving and optimization write-up for a new multimodal MoE model, with architecture, kernel, quantization, speculative decoding, benchmarking, and accuracy evidence; highly relevant to AI infrastructure, though partly vendor-promotional.

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

0.56total under rubric v2.3Contestedjudges differ by 0.54 on promotional

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.57
  • Reader interest0.70
  • Audience breadth0.49
  • Practical relevance0.69
  • Substantiated0.74
  • Technical depth0.93
  • New information0.93
  • Counts against: Promotional0.38
  • Counts against: Overclaim0.26

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?0.630.450.630.570.18+0.24+0.137
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.690.600.800.700.20+0.26+0.181
Audience breadthHow many people who build technology does it concern?0.520.400.550.490.15+0.13+0.064
Practical relevanceHow useful is it to someone who builds software or tech products?0.690.600.780.690.18+0.22+0.152
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.0.780.600.840.740.24+0.05+0.037
Technical depthHow technically substantive is it?0.990.850.940.930.14+0.05+0.046
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.900.900.990.930.09+0.05+0.047
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.0.080.450.620.380.54 , above the contested threshold−0.19−0.073
OverclaimDo the headline or conclusions claim more than the body supports?0.290.300.180.260.12−0.11−0.028
Sum of contributions+0.563
Claim-check penalty0.000
Total, as published0.563

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 #137 on Rubric, 13 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-13/137/"><img src="https://rubric.hrih.si/badge/2026-11-13/137.svg" alt="Ranked #137 on Rubric, 13 Nov 2026" width="252" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN —

Recorded for context only, checked 15 Nov 2026, 20:42 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 “Inkling 2 Small on vLLM: Day-0 Support”

More on Rubric

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