[dead]
Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
11–20 of 59 posts
Re: Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
#12As of now, 3 of the 5 comments on this page are just 0-1 karma accounts high-fiving the article. Suspicious.
You can play with it online. I was pretty impressed with the speed/quality given it's size.
It's definitely not going to replace a larger frontier model, but it's worth keeping an eye on.
Re: Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
#13I wish that "small" LLMs would stop being confidently very incorrect. Admittedly this is a bit of an intentionally esoteric test, but the confident way in which it presents a totally incorrect answer is a bit concerning.
"please write 250 words on the etymology and history of the word schlong"
The actual origin of the word is from middle high German and Yiddish-speaking Ashkenazi Jewish communities.
For comparison qwen 3.6 35B A3B does perfect on this and will give a solid description of the word's real origins and how it has made it into casual profanity/vulgarity as used in US English, and even mentions specific stand-up comedians and famous public figures of specific ethnic/religious origin in the US NE who introduced it into wider use.
Ask it for something that's not a narrow niche scientific or technical field, but something that would be less common to make it into a 20B size model, and see just how it does.
chat test link: https://chat.deepgrove.ai/
Re: Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
#14A benchmark table comparing to Qwen 3.5 35B-A3B seems strange when Qwen 3.6 35B-A3B has been out for some time and is significantly better.
I didn't notice the version difference when first reading the article! So this is a heads up to people like me.
Re: Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
#15For small models like this, it’s super important that it works well at tool calling etc. imho because it can’t memorize facts and isn’t big enough to tell when it doesn’t know. I could use it for high quality tool routing or a backup fast model for smaller task set. E.g. I use GPT-5.6 for voice channels at home. I’d prefer to be able to have this do basic tool calls and stuff because of the local speed.
Will give it a crack as a quick model in my clawlike.
Re: Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
#16For small models like this, it’s super important that it works well at tool calling etc. imho because it can’t memorize facts and isn’t big enough to tell when it doesn’t know. I could use it for high quality tool routing or a backup fast model for smaller task set. E.g. I use GPT-5.6 for voice channels at home. I’d prefer to be able to have this do basic tool calls and stuff because of the local speed. Will give it…
This matches what I've seen shipping Apple's on-device model in a Mac app.
The model is reliable at the semantic half. Give it the OCR text of a receipt and it correctly identifies the vendor and the date. What it does not do reliably is follow mechanical instructions. A user asked for dates formatted as TT-MM-JJJJ and got files literally named TT-MM-JJJJ, because it reproduced the format string instead of filling it in. Another asked for uppercase, and the model acknowledged the request in its reasoning and returned lowercase.
The failures were not consistent, which is worse than failing every time. You cannot tell users "this doesn't work", only "this works most of the time", and nobody accepts that from something touching their files.
What fixed it was moving the mechanical part out of the model entirely. The model decides what the document is about; ordinary deterministic code decides how the name is written. Every time I moved that line back toward the model, quality dropped.
Which is a version of your point: with a small model the win isn't making it smarter, it's shrinking what you make it responsible for.
Re: Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
#17I wish that "small" LLMs would stop being confidently very incorrect. Admittedly this is a bit of an intentionally esoteric test, but the confident way in which it presents a totally incorrect answer is a bit concerning. "please write 250 words on the etymology and history of the word schlong" https://pastes.io/uhshFgn4 The actual origin of the word is from middle high German and Yiddish-speaking Ashkenazi Jewish com…
lol I like the first one though. Reads like a great sarcasm response.
I wonder if kids will do this to their parents.
Re: Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
#18Anyone compare this to ternary bonsai vs the 1 bit
Re: Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
#19I wish that "small" LLMs would stop being confidently very incorrect. Admittedly this is a bit of an intentionally esoteric test, but the confident way in which it presents a totally incorrect answer is a bit concerning. "please write 250 words on the etymology and history of the word schlong" https://pastes.io/uhshFgn4 The actual origin of the word is from middle high German and Yiddish-speaking Ashkenazi Jewish com…
Would it not be better to ask models to search the topic on the Internet and then answer? I do not understand why we expect small LLMs to answer from own knowledge.
Re: Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone
#20I wish that "small" LLMs would stop being confidently very incorrect. Admittedly this is a bit of an intentionally esoteric test, but the confident way in which it presents a totally incorrect answer is a bit concerning. "please write 250 words on the etymology and history of the word schlong" https://pastes.io/uhshFgn4 The actual origin of the word is from middle high German and Yiddish-speaking Ashkenazi Jewish com…
Small or overly quantized LLMs are a genre of humor. Same goes for small image generators. Janky generative AI is like the Geocities web pages of today.