Maple-Preview
Ranked 3 of 4 quantized language models by recommenders
People recommend it as a fast, capable small ternary model that runs on an iPhone at about 120 tokens per second. Critics say it hallucinates facts and gives confident wrong answers.
People recommend it as a fast, capable small ternary model that runs on an iPhone at about 120 tokens per second. Critics say it hallucinates facts and gives confident wrong answers.
7 people gave an opinion
- recommend it
- 6
- criticize it
- 1
- approval share
- 86%
Recommended in 1 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- 6 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 1 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Trained from scratch in ternary format
“really cool to see one trained from scratch in the ternary format”
Comment from 5 Aug 2026 in “Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone” Fast and good for its size
“I was pretty impressed with the speed/quality given it's size.”
Comment from 4 Aug 2026 in “Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone”
What people warn about
Each mark is one comment
Hallucinates knowledge and gives confident errors
“much like the bonsai tenary one it hallucinates knowledge quite aggressively”
Comment from 4 Aug 2026 in “Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone” “I wish that "small" LLMs would stop being confidently very incorrect.”
Comment from 4 Aug 2026 in “Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone” Self-improvement claims seem doubtful
“I'm not sure I buy it will actually be able to self-improve”
Comment from 5 Aug 2026 in “Show HN: Maple-Preview – ternary 20B MoE running at 120 tok/s on a iPhone”
Other quantized language models people recommend
The three most recommended other quantized language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Microsoft BitNet | 16 | 9 | 64% | 4 | — | — |
| Ternary Bonsai | 14 | 8 | 64% | 3 | — | — |
| Maple-PreviewThis page | 6 | 1 | 86% | 1 | — | — |
| BitNet b1.58 2B4T | 5 | 1 | 83% | 4 | — | — |
What people said
5 of the 7 comments that mention it, newest first. Each links to the original comment.
“I'm not sure I buy it will actually be able to self-improve”
“really cool to see one trained from scratch in the ternary format”
“I wish that "small" LLMs would stop being confidently very incorrect.”
“I was pretty impressed with the speed/quality given it's size.”
“much like the bonsai tenary one it hallucinates knowledge quite aggressively”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.