Needle 26M
Ranked 4 of 4 tool-calling models by recommenders
Recommended as a small model for agentic tool calling on on-device systems. Critics report inconsistent results, CPU errors, and invented details.
Recommended as a small model for agentic tool calling on on-device systems. Critics report inconsistent results, CPU errors, and invented details.
9 people gave an opinion
- recommend it
- 6
- criticize it
- 3
- approval share
- 67%
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: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not 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.
- 2 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
Praised as excellent, needed work
“Smaller tool calling models are absolutely needed when we are trying to apply agentic workflow to on-device, small systems”
Comment from 14 May 2026 in “Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model” “This is some excellent work Henry!”
Comment from 12 May 2026 in “Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model”
Other tool-calling models people recommend
The three most recommended other tool-calling 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 |
|---|---|---|---|---|---|---|
| Needle2 | 51 | 22 | 70% | 5 | — | Approved |
| FunctionGemma | 11 | 2 | 85% | 3 | — | — |
| Cactus Needle 3 | 10 | 12 | 45% | 1 | — | — |
| Needle 26MThis page | 6 | 3 | 67% | 1 | — | — |
What people said
8 of the 9 comments that mention it, newest first. Each links to the original comment.
“Smaller tool calling models are absolutely needed when we are trying to apply agentic workflow to on-device, small systems”
“it made up a meeting that I didn't mention”
“I tried a few times it wasnt working! Maybe its a hit or miss?”
“I'd expect either a chain load or just a 2 hour timer. Further attempts humorously give two separate 1-hour-timers.”
“No FFN is blowing my mind.”
“This is some excellent work Henry!”
“Got a bunch of errors trying to run it on CPU though.”
“Looks like you need to open up access to”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.