Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

froggeric
/
Qwen-Fixed-Chat-Templates

MLX
jinja
chat-template
qwen
qwen3.5
qwen3.6
lm-studio
llama.cpp
vllm
tool-calling
thinking
Model card Files Files and versions
xet
Community
32

Instructions to use froggeric/Qwen-Fixed-Chat-Templates with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use froggeric/Qwen-Fixed-Chat-Templates with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir Qwen-Fixed-Chat-Templates froggeric/Qwen-Fixed-Chat-Templates
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Will this work on spicyneuron/Qwen3.5-397B-A17B-MLX-2.6bit ?

1
#32 opened about 13 hours ago by
openSourcerer9000

this template save my day.

#31 opened 2 days ago by
rosspanda0

Reasoning off mode issue

πŸ‘ 3
5
#30 opened 7 days ago by
GergelyZsolt

Still issues with tooling from time to time....

#29 opened 7 days ago by
boldos

inference throughput drops by 80% with this template

14
#28 opened 12 days ago by
froilo

Response will sometimes show full thought process to Frigate, which will fail to create a GenAI Summary

#27 opened 13 days ago by
ampersandru

toolcall inside thinking

πŸ‘€ 3
5
#25 opened 15 days ago by
snapo

Model abrupt stop and thinking stop whenever tool calls contain unicode

5
#24 opened 15 days ago by
ManyOtherFunctions

Keeps emitting <tool_call> json into the context

βž• 1
3
#23 opened 15 days ago by
theliphant

v19 released with major improvements

β€οΈπŸš€ 17
22
#22 opened 18 days ago by
froggeric

`preserve_thinking` flag ignored?

2
#9 opened 24 days ago by
astride-thee-squid

Gemma 4 template request

πŸ‘ 2
3
#4 opened 26 days ago by
OnesimusTheLesser
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs