Running a Language Model on a $35 FPGA
Comments on “Running a Language Model on a $35 FPGA”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
Nishta Hirani-Nelson's write-up describes running a 1.07M-parameter Transformer language model on a $35 iCE40UP5K FPGA with only open-source tooling and no softcore CPU. It is notable because the design fits in about 144 KB of memory and integer-only arithmetic, using a mixture-of-experts layer, rotary embeddings, and gated delta nets, generating…
Why it ranked
No. 25 of 46 with a score of 0.55. The panel rated it highest on new information (0.92) and technical depth (0.87), lowest on audience breadth (0.41). Placed No. 25, No. 46 by score alone: the placement terms moved other stories past it.
- AI judgeJudge 2claude-haiku-5-5
- Detailed, technically specific engineering writeup of a small LLM on an iCE40 FPGA with measured utilization; novel and practical for hardware-minded builders but niche and a personal side project.
- AI judgeJudge 3gpt-5.6-luna
- A technically detailed, reproducible FPGA/LLM build with architecture, quantization, resource constraints, utilization, code, and a demo. It is highly relevant to AI-hardware practitioners, though its broader impact remains niche and performance evaluation is limited.
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
0.55total under rubric v2.3
- Significance0.45
- Reader interest0.70
- Audience breadth0.41
- Practical relevance0.47
- Substantiated0.81
- Technical depth0.87
- New information0.92
- Counts against: Promotional0.04
- Counts against: Overclaim0.16
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? | 0.47 | 0.30 | 0.56 | 0.45 | 0.26 | +0.24 | +0.107 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.59 | 0.70 | 0.82 | 0.70 | 0.23 | +0.26 | +0.183 |
| Audience breadthHow many people who build technology does it concern? | 0.46 | 0.40 | 0.38 | 0.41 | 0.08 | +0.13 | +0.054 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.45 | 0.35 | 0.61 | 0.47 | 0.26 | +0.22 | +0.103 |
| 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 | 0.60 | 0.86 | 0.81 | 0.36 | +0.05 | +0.040 |
| Technical depthHow technically substantive is it? | 0.92 | 0.80 | 0.90 | 0.87 | 0.12 | +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 | 0.98 | 0.92 | 0.10 | +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. | 0.05 | 0.05 | 0.03 | 0.04 | 0.02 | −0.19 | −0.008 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.23 | 0.20 | 0.05 | 0.16 | 0.18 | −0.11 | −0.018 |
| Sum of contributions | +0.551 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.551 | ||||||
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/2026-11-09/25/"><img src="https://rubric.hrih.si/badge/2026-11-09/25.svg" alt="Ranked #25 on Rubric, 9 Nov 2026" width="238" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 1 pts, not on front page
Recorded for context only, checked 9 Nov 2026, 05:46 UTC. It played no part in the ranking.