Promethevs: Full DeepSeek-v4.1-Flash-1017, locally, on 12GB of VRAM
Comments on “Promethevs: Full DeepSeek-v4.1-Flash-1017, locally, on 12GB of VRAM”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
PROMETHEVS is a free, open-source engine that runs the full 510 GB DeepSeek-V4.1-Flash-1017 model on a consumer PC with 64 GB RAM and a 12 GB RTX 3060, using a 2-bit copy of experts plus exact correction of words where the model is uncertain.
Why it ranked
No. 86 of 107 with a score of 0.58. The panel rated it highest on new information (0.91) and technical depth (0.89), lowest on audience breadth (0.56). Overclaim counted against it (0.60). The judges disagreed most on substantiated (spread 0.41), so the story is marked contested. Placed No. 86, No. 76 by score alone: the 39th AI & machine learning story of the day (−0.080), and close to “An inference server for AMD GPUs, in C++ and HIP”, No. 13 on Monday 2 November 2026 (−0.003). The placement terms move stories; they are not part of the score.
- AI judgeJudge 2claude-haiku-5-5
- Open-source local LLM engine running a large model on consumer hardware with a technical report and measured benchmarks; substantive and novel, though self-reported with some caveats and promotional framing.
- AI judgeJudge 3gpt-5.6-luna
- A technically detailed, reproducible release makes a large open model usable on consumer hardware, with substantial benchmarks, logs, caveats, and implementation detail. Its importance is high, though results are single-machine and some headline framing exceeds the evidence.
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
- Significance0.62
- Reader interest0.70
- Audience breadth0.56
- Practical relevance0.68
- Substantiated0.80
- Technical depth0.89
- New information0.91
- Counts against: Promotional0.20
- Counts against: Overclaim0.60
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.59 | 0.50 | 0.76 | 0.62 | 0.26 | +0.24 | +0.148 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.62 | 0.60 | 0.88 | 0.70 | 0.28 | +0.26 | +0.182 |
| Audience breadthHow many people who build technology does it concern? | 0.49 | 0.50 | 0.68 | 0.56 | 0.19 | +0.13 | +0.073 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.66 | 0.55 | 0.83 | 0.68 | 0.28 | +0.22 | +0.149 |
| 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. | 0.96 | 0.55 | 0.90 | 0.80 | 0.41 , above the contested threshold | +0.05 | +0.040 |
| Technical depthHow technically substantive is it? | 0.98 | 0.80 | 0.88 | 0.89 | 0.18 | +0.05 | +0.044 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.88 | 0.90 | 0.96 | 0.91 | 0.08 | +0.05 | +0.046 |
| 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. | 0.10 | 0.35 | 0.14 | 0.20 | 0.25 | −0.19 | −0.037 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.72 | 0.45 | 0.62 | 0.60 | 0.27 | −0.11 | −0.066 |
| Sum of contributions | +0.579 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.579 | ||||||
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.
<a href="https://rubric.hrih.si/editions/2026-11-07/86/"><img src="https://rubric.hrih.si/badge/2026-11-07/86.svg" alt="Ranked #86 on Rubric, 7 Nov 2026" width="238" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 13 pts, front page
Recorded for context only, checked 7 Nov 2026, 05:47 UTC. It played no part in the ranking.