https://huggingface.co/nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-BF16

#2281
by nightmedia - opened

Dear Team Radermacher

This one is open, but would be nothing without your expert-created quants.

So, would you mind creating a set?

https://huggingface.co/nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-BF16

This model is a NuSLERP merge using Qwen3.6-27B as a base:

  • nightmedia/Qwen3.6-27B-Architect-DS9
  • DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking

It contains distills of:

  • Claude 4.6
  • Polaris Alpha
  • Star Trek TNG
  • Philip K Dick

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.699,0.871,0.910
q8-hi    0.694,0.865,0.910
mxfp4    0.694,0.872,0.909

Quant    Perplexity      Peak Memory   Tokens/sec
q8-hi    3.895 ± 0.025   37.26 GB      215
mxfp8    3.921 ± 0.025   34.74 GB      218
qx86-hi  3.898 ± 0.025   32.36 GB      218
qx64-hi  3.918 ± 0.025   25.64 GB      217
mxfp4    3.999 ± 0.025   21.30 GB      225

Components

Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking
mxfp8    0.673,0.846,0.905

Qwen3.6-27B-Architect-DS9
mxfp8    0.695,0.871,0.911
mxfp4    0.692,0.872,0.909

Baseline model

         arc   arc/e boolq hswag obkqa piqa  wino
Qwen3.6-27B-Instruct
mxfp8    0.647,0.803,0.910,0.773,0.450,0.806,0.742
qx86-hi  0.637,0.798,0.911,0.775,0.442,0.807,0.737

This model is using the fixed jinja template from froggeric/Qwen-Fixed-Chat-Templates

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.

I added a similar set of tags for handling the preserve_thinking flag:

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

Holodeck templates

Jinja templates available:

  • No system profile
    • chat_template_json.jinja
    • chat_template_xml.jinja
  • Profiled with DS9 Holodeck
    • chat_template_holodeck_json.jinja
    • chat_template_holodeck_xml.jinja

The xml have tool formatting as XML.

-G

As always, Im here to queue it, enjoy =)

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#Qwen3.6-27B-Architect-DS9-Polaris-Heretic-BF16-GGUF for quants to appear.

Sign up or log in to comment