Froggeric Qwen Fixed Chat Templates
Hacker ApprovedChat template in AI tools
Community-made Jinja chat templates for Qwen models that fix tool calling and effort selection and let users reduce or turn off thinking.
Community-made Jinja chat templates for Qwen models that fix tool calling and effort selection and let users reduce or turn off thinking.
10 people gave an opinion
- recommend it
- 10
- criticize it
- 0
- approval share
- 100%
Recommended in 4 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: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 10 people recommend itNeeds 10 or more, met.
- Nobody criticizes itNeeds 2 to 1 or better, met.
- Recommended in 4 of 13 monthsNeeds 4 or more, 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
Fixes upstream Qwen template bugs
“there is a template that is supposed to fix the updates for the Qwen Models”
Comment from 18 May 2026 in “Qwen 3.7 Preview” “These templates actually fix the effort selection for LM Studio/3.8”
Comment from 15 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet” “one of the bugfixed chat templates like the Froggeric version”
Comment from 22 Jul 2026 in “Nvidia DGX Spark as a daily driver” - Comment from 17 Aug 2026 in “Qwen 3.8 27B is excellent, but it defaults to overthinking things”
Reduces or turns off thinking
“use this [0] to reduce or turn off thinking, fix tool calling, keep a 100% KV cache hit rate”
Comment from 14 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet” “set thinking to minimal and use these jinja templates”
Comment from 27 Aug 2026 in “GLM-5.3-Flash” “Reduce or turn down thinking:”
Comment from 14 Aug 2026 in “Qwen3.8-27B” - Comment from 14 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet”
Fixes effort selection and tool calling
“use this [0] to reduce or turn off thinking, fix tool calling, keep a 100% KV cache hit rate”
Comment from 14 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet” “Given that it apparently defaults to 'xhigh', this is probably the answer.”
Comment from 14 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet” “These templates actually fix the effort selection for LM Studio/3.8”
Comment from 15 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet” Recommended by many Hacker News users
“Oh, that's cool, I saw those and I did wonder!”
Comment from 15 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet” “Thank you, this is exactly what I needed.”
Comment from 14 Aug 2026 in “Qwen 3.8 27B is out: open weights, best local dense model yet” “Don't sleep on the froggeric templates.”
Comment from 1 Sep 2026 in “Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s” - Comment from 5 Sep 2026 in “Corporate America is getting hooked on open-source AI”
What people said
15 of the 16 comments that mention it, newest first. Each links to the original comment.
“remember to use froggeric template”
“Don't sleep on the froggeric templates.”
“set thinking to minimal and use these jinja templates”
“it fixes some issues I saw with the upstream versions”
“Oh, that's cool, I saw those and I did wonder!”
“These templates actually fix the effort selection for LM Studio/3.8”
“bumped my agent success rate from 67% to 92.5%”
“I've had to fix I think one issues with that one but it's better.”
“Given that it apparently defaults to 'xhigh', this is probably the answer.”
“Thank you, this is exactly what I needed.”
“Reduce or turn off thinking”
“use this [0] to reduce or turn off thinking, fix tool calling, keep a 100% KV cache hit rate”
“Reduce or turn down thinking:”
“one of the bugfixed chat templates like the Froggeric version”
“there is a template that is supposed to fix the updates for the Qwen Models”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.