---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE
base_model: Qwen/Qwen3.6-27B
pipeline_tag: text-generation
tags:
- dense
- coding
- agentic
- unimodal
- repackaged
---

<center>
<img style='height: 16em' src='https://cdn-uploads.huggingface.co/production/uploads/63e9a1c4ccae1fe5c622b9f6/ADYJx3gsTmTVPuhHGMM5S.webp'/>
</center>

# Focus

repackaged [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B) with a simplified architecture and minor opinionated improvements

- all vision-related components removed
- reduced storage and memory, faster inference
- zero loss of output quality

## comparison

<table>
<tr>
  <th></th>
  <th>Qwen 3.6 27B</th>
  <th>Focus</th>
</tr>
<tr>
  <td>author</td>
  <td><a href='https://huggingface.co/Qwen'>Alibaba Qwen</a></td>
  <td><a href='https://huggingface.co/Jaidchen'>Jaid</a></td>
</tr>
<tr>
  <td>repository</td>
  <td><a href='https://huggingface.co/Qwen/Qwen3.6-27B'>Qwen/Qwen3.6-27B</a></td>
  <td><a href='https://huggingface.co/Jaidchen/Focus'>Jaidchen/Focus</a></td>
</tr>
<tr>
  <td>architecture</td>
  <td><code>qwen3_5</code></td>
  <td><code>qwen3_5_text</code></td>
</tr>
<tr>
  <td>Transformers handler</td>
  <td>
  <a href='https://huggingface.co/docs/transformers/model_doc/qwen3_5#transformers.Qwen3_5ForConditionalGeneration'><code>Qwen3_5ForConditionalGeneration</code></a>
  </td>
  <td>
  <a href='https://huggingface.co/docs/transformers/model_doc/qwen3_5#transformers.Qwen3_5ForCausalLM'><code>Qwen3_5ForCausalLM</code></a>
  </td>
</tr>
<tr>
  <td>tensor entries</td>
  <td>1199</td>
  <td>866</td>
</tr>
<tr style='opacity: 50%'>
  <td>tensor type</td>
  <td>bf16</td>
  <td>bf16</td>
</tr>
<tr>
  <td>parameters</td>
  <td>27 781 427 952</td>
  <td>27 320 697 856</td>
</tr>
<tr style='opacity: 50%'>
  <td>vocabulary size</td>
  <td>248 320</td>
  <td>248 320</td>
</tr>
<tr style='opacity: 50%'>
  <td>context size</td>
  <td>262 144</td>
  <td>262 144</td>
</tr>
<tr style='opacity: 50%'>
  <td>MTP</td>
  <td>integrated</td>
  <td>integrated</td>
</tr>
<tr>
  <td>sampling strategy</td>
  <td>random sampling</td>
  <td>greedy/deterministic</td>
</tr>
<tr>
  <td>sampling parameters</td>
  <td>
    <div style='font-family: Jaidevka Code, JetBrains Mono, monospace; line-height: initial'>
      <span style='color: hsl(from currentColor 0 100% l)'>do_sample</span>: <span style='color: hsl(from currentColor 50 80% l)'>true</span><br>
      <span style='color: hsl(from currentColor 0 100% l)'>temperature</span>: <span style='color: hsl(from currentColor 50 80% l)'>0.6</span><br>
      <span style='color: hsl(from currentColor 0 100% l)'>top_k</span>: <span style='color: hsl(from currentColor 50 80% l)'>20</span><br>
      <span style='color: hsl(from currentColor 0 100% l)'>top_p</span>: <span style='color: hsl(from currentColor 50 80% l)'>0.95</span></div>
  </td>
  <td>
    <div style='font-family: Jaidevka Code, JetBrains Mono, monospace; line-height: initial'>
      <span style='color: hsl(from currentColor 0 100% l)'>do_sample</span>: <span style='color: hsl(from currentColor 50 80% l)'>false</span>
    </div>
  </td>
</tr>
<tr>
  <td>input modality</td>
  <td>text, image, video</td>
  <td>text</td>
</tr>
<tr>
  <td>repository size</td>
  <td>55 586 101 650</td>
  <td>54 664 408 333</td>
</tr>
<tr>
  <td>model size</td>
  <td>55 562 855 904</td>
  <td>54 641 395 712</td>
</tr>
<tr>
  <td>splits</td>
  <td>11</td>
  <td>none</td>
</tr>
<tr>
  <td>Jinja template</td>
  <td><a href='https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/chat_template.jinja'>Qwen original</a></td>
  <td><a href='https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/chat_template.jinja'>Qwen original</a> + <a href='https://huggingface.co/unsloth/Qwen3.5-27B/blob/main/chat_template.jinja'>Unsloth tweaks</a> + custom unimodality patch</td>
</tr>
</table>

## pros

- reduced storage needs
- reduced loading time
- reduced VRAM occupancy, thus more room for context
- increased inference speed
- simplified architecture, unlocking some further potential for optimizing low-level procedures

## cons

- legally blind
  - Pictures and video frames can still be present in the context without crashing, but their contents are no longer interpreted by the model and won’t do anything else than waste space.
  - If you occasionally rely on those capabilities, I suggest adding a `consult` tool to your harness that calls a vision-enabled subagent model like [Gemini Flash](https://openrouter.ai/~google/gemini-flash-latest) or [GPT](https://openrouter.ai/~openai/gpt-latest).
- reduced compatibility
  - The applied coercions may confuse your inference engine in case it has fixed expectations about the model’s architecture and thus lead to unpredictable behavior.
  - The simplified architecture is handled by the `Qwen3_5ForCausalLM` class which may not be included in your inference engine. In this case you would need to ask your agent or integrate it yourself.

## caveats

- model file not split, possibly causing issues if intended to be stored on an HDD from the previous century
- random sampling disabled by default, less suitable for long-form writing, entertainment and casual chat

## license

Apache 2.0, derived from [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE)