o
openharmony-models/Qwen-Fixed-Chat-Templates
Model Introduction
Files & versions
Pull Requests
Discussion
Analysis

Fixed Chat Templates for Qwen 3.5 & 3.6

2026-05-05 — Reviewed against community merged templates (allanchan339, fakezeta). Confirmed all useful features already present; from_json string-arg parsing not portable to C++ engines. Added auto-close unclosed thinking, thanks to allanchan339.

Drop-in Jinja templates that fix rendering errors, token waste, and missing features in the official Qwen chat templates. Works in LM Studio, llama.cpp, vLLM, MLX, oMLX, and any engine that supports HuggingFace Jinja templates.

Why you need this

The official Qwen templates have bugs that break real usage:

ProblemImpact
Tool calls fail on C++ engines`
developer role rejectedModern APIs send it; the official template raises an error
Empty thinking blocks spam contextEvery past turn gets wrapped in tags, even with nothing inside
No way to toggle thinkingYou're stuck with whatever the model defaults to
Qwen 3.6: </thinking> hallucinationModel sometimes generates the wrong closing tag; parser fails
No-user-query exception breaks tool callingraise_exception crashes agentic loops and resets in OpenClaw and similar runtimes
Unclosed thinking before tool callModel starts reasoning then calls a tool without closing thinking block — malformed output

All seven are fixed here, plus a clean <|think_on|> / <|think_off|> toggle you can drop into any message.

Quick install

LM Studio

  1. Open your Qwen model in the right-side panel
  2. Scroll to Prompt Template
  3. Replace the template with the contents of qwen3.5/chat_template.jinja or qwen3.6/chat_template.jinja
  4. Save

llama.cpp / koboldcpp

--jinja --chat-template-file qwen3.6/chat_template.jinja

vLLM / TextGen

Replace the chat_template string in your tokenizer_config.json with the file contents.

oMLX

Overwrite chat_template.jinja in your local model directory. Load with --jinja. Remove any chat_template_kwargs overrides — the template handles everything internally.

Which file do I use?

FileFor models
qwen3.5/chat_template.jinjaQwen3.5-35B-A3B, Qwen3.5-32B, Qwen3.5-14B, and all Qwen 3.5 variants
qwen3.6/chat_template.jinjaQwen3.6-27B, Qwen3.6-35B-A3B, and all Qwen 3.6 variants

The 3.6 template is a superset — it additionally handles preserve_thinking, </thinking> hallucination recovery, and interrupted thought streams. If you're on 3.6, use the 3.6 file.

Thinking toggle

Drop <|think_on|> or <|think_off|> anywhere in your system or user prompt. The template intercepts the tag, removes it from context so the model never sees it, and flips the mode.

Fast answer, no reasoning:

System: You are a coding assistant. <|think_off|>
User: What's 2+2?

Deep reasoning:

System: You are a coding assistant. <|think_on|>
User: Implement a red-black tree in Rust.

The tag syntax (<|think_on|>, <|think_off|>) uses Qwen's control-token delimiters, so it will never collide with real text. Earlier community templates used /think, which broke legitimate paths like cd /mnt/project/think.

Pre-installed models

These templates are already bundled with:

  • froggeric/Qwen3.6-27B-MLX-8bit
  • froggeric/Qwen3.6-27B-MLX-4bit
  • froggeric/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-MLX-8bit
  • froggeric/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-MLX-4bit
  • froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-8bit
  • froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-6bit
  • froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-4bit
  • froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-8bit
  • froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-6bit
  • froggeric/Qwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bit

If you're using one of those, you already have the template. This repo is for everyone else.


Technical details — what exactly was fixed

Tool calls on C++ engines

The official template iterates tool call arguments with |items:

{%- for key, value in tool_call.arguments|items %}

Python's Jinja supports |items. C++ runtimes (LM Studio, llama.cpp, MLX) do not — the template produces a rendering error instead of output. This template uses direct dictionary key lookups instead:

{%- for args_name in tool_call.arguments %}
    {%- set args_value = tool_call.arguments[args_name] %}

It also replaces is sequence with is iterable (stricter C++ runtimes require it), removes |safe wrappers (also Python-only), and handles arguments returned as raw strings instead of objects.

developer role

The OpenAI-compatible API spec sends message.role == "developer" for system-level instructions. The official Qwen template only checks for "system" and throws on anything else. Both templates here accept "developer" and map it to the system role.

Empty thinking blocks

The official template wraps every past assistant turn in thinking tags:

<|im_start|>assistant
<think/>
</think >

Here is the answer...

When there's no reasoning content, those tags are dead weight — they waste context tokens and break prefix caching. The Qwen 3.5 template checks reasoning_content before emitting. The Qwen 3.6 template goes further: it respects the preserve_thinking kwarg, checks reasoning_content|trim|length > 0, and ties history visibility to the <|think_off|> override.

</thinking> hallucination (Qwen 3.6 only)

The Qwen 3.6 model sometimes generates </thinking> instead of the expected closing tag. The official parser splits on </think > only and fails. The 3.6 template detects which closing tag was actually used and splits on that:

{%- if '</think >' in content %}
    {%- set think_end_token = '</think >' %}
{%- elif '</thinking>' in content %}
    {%- set think_end_token = '</thinking>' %}

It also handles interrupted generation (max tokens hit mid-thought) by rescuing incomplete streams instead of injecting broken tag pairs.

Arguments serialization

The official template serializes argument values with |tojson unconditionally, which turns Python True into JSON true correctly but fails when the value is already a string. The fixed templates check the type first — strings pass through as-is, everything else goes through |tojson.

Auto-close unclosed thinking before tool calls

The model sometimes starts a thinking block and then immediately calls a tool without emitting the closing tag. The official template doesn't handle this — the unclosed thinking tag bleeds into the tool call, producing malformed output. Both fixed templates detect this pattern and auto-inject the closing tag before the tool call boundary.

No-user-query exception

The official template scans the message list in reverse to find the last "real" user query (skipping tool-result wrappers). If all user messages are tool results — or there are no user messages at all — it fires raise_exception('No user query found in messages.') and the template hard-crashes.

This breaks real usage:

  • Agentic tool-calling chains where the conversation ends with tool results and no fresh user query
  • After /reset or /new in runtimes like OpenClaw, where tool results from a prior session persist without a new user message
  • System-only contexts with no user messages

The fix replaces the exception with a graceful fallback: {%- set ns.last_query_index = messages|length - 1 %}. The thinking display logic then degrades naturally — assistant turns with reasoning content still show thinking tags when preserve_thinking is enabled.

Comparison — Qwen 3.5 templates
FeatureOfficialLuffyTheFoxmod-ellaryPneunyThis
Tool argumentsFailsFixedMissingFixedFixed
|safe removedFailsFixedMissingFixedFixed
developer roleMissingMissingMissingMissingAdded
Thinking toggleNoneNone/think (system only)None<|think_off|> anywhere
Empty think in historyBrokenBrokenTags omittedBrokenFixed
Text safetyN/AN/ABreaks on /think in pathsN/ASafe
Clean instructionsYesYesYesInjects "I cannot call a tool"Yes
No-user-query crashCrashesCrashesCrashesCrashesGraceful fallback
Auto-close thinking before toolNot handledNot handledNot handledNot handledAuto-injects close tag
Comparison — Qwen 3.6 template
FeatureOfficialThis
Tool argumentsFails (|items)Fixed
|safe removedFailsFixed
developer roleMissingAdded
Thinking toggleNone<|think_off|> anywhere
preserve_thinkingSpams empty blocksDynamic length checks
</thinking> hallucinationFailsDetected and handled
Interrupted streamsBroken tagsRescued
Auto-close thinking before toolNot handledAuto-injects close tag
No-user-query crashCrashesGraceful fallback

Authorship

RoleAuthor
Original modelsAlibaba Cloud (Qwen team)
Template fixesfroggeric

License

Apache-2.0, inherited from Qwen.