Q

Qwen3.5-27B-Writer-Derestricted

Writing

No ratings yet(0)
Prose
—(0)
Intelligence
—(0)
Knowledge
—(0)
Instruction Following
—(0)
Coding
—(0)
Steerability
—(0)

Ratings reflect this model as run on Arli AI.

Qwen3.5-27B-Writer-Derestricted is a text generation model available on Arli AI. It offers 27B parameters, 262K token context, reasoning support, vision input. Recommended use: Writing. Run it through the OpenAI-compatible chat completions API with unlimited requests and zero-log privacy.

View on Hugging FaceBack to Models

Hourly Usage

Token Usage

Input (24H)

5K

Output (24H)

662

Input (7D)

54K

Output (7D)

26K

Performance Metrics

Typical Total Time

3.18s

Typical TTFT

1.16s

Typical Input TPS

2478.63

Typical Output TPS

30.69

Model Information

Context Size

262144

Quantization

r64 on INT8

Engine

vllm

Creation Method

Finetune

Model Class

Qwen3.5-27B-D - LoRA-DRS

Chat Template

Qwen3.5

Reasoning

Yes

Vision

Yes

Parameters

27B

Added At

4/4/2026

Use Qwen3.5-27B-Writer-Derestricted with the Arli AI API

Qwen3.5-27B-Writer-Derestricted is available through an OpenAI-compatible chat completions endpoint. Point any OpenAI SDK at https://api.arliai.com/v1, pass Qwen3.5-27B-Writer-Derestricted as the model, and requests are served without logging.

cURL

curl https://api.arliai.com/v1/chat/completions \
  -H "Authorization: Bearer $ARLIAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen3.5-27B-Writer-Derestricted",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.arliai.com/v1",
    api_key="YOUR_ARLIAI_API_KEY",
)

response = client.chat.completions.create(
    model="Qwen3.5-27B-Writer-Derestricted",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

See the text generation docs for every parameter, or read the quick start guide to make your first request.


license: apache-2.0 datasets:

  • ConicCat/Gutenberg-SFT
  • PJMixers-Dev/C2-Logs-Sonnet-4.5-all
  • ConicCat/AntiRep
  • ConicCat/Condor-SFT-Filtered base_model:
  • Qwen/Qwen3.5-27B

ConicCat/Qwen3.5-27B-Writer

A writing & roleplay finetune of Qwen3.5 27B. The primary emphasis is on writing quality as it strongly generalizes across both domains. This model is also trained from ConicCat/Qwen3.5-Antirep-27B to mitigate repetition issues.

The basic idea is to use a curriculum learning setup to overcome the lack of high quality roleplay data by first training on lower quality roleplay data, then training on higher quality writing data. Starting from ConicCat/Qwen3.5-Antirep-27B, the model was trained on a roughly equal mixture of instruct / roleplay / writing data for three epochs. The model was then trained for eleven epochs on a smaller dataset of short story anthologies by critically acclaimed authors.

Recommended Settings

  • Chatml template with <think>\n\n</think> or {{char}}: prefill. Only non-thinking was trained, but thinking probably still works.
  • temperature = 0.7
  • top_p = 0.95
  • I do not recommend using high rep pen values like Qwen suggests for the base model. rep_pen = 1.05 or a moderate dry setting should suffice.
  • For quants, Q4_K_M runs well with ~100k context on 24GB Vram
  • IQ4_XS should fit on 16GB Vram with about 20-24k context with the vulkan backend, although it's pretty tight and may require some fiddling around with open programs e.t.c.

Datasets

  • ConicCat/AntiRep to mitigate repetitition.
  • internlm/Condor-SFT-20K for instruct; even though instruct capabilities are not the primary focus, adding some instruct data helps mitigate forgetting and maintains general intellect and instruction following capabilites.
  • PJMixers-Dev/C2-Logs-Sonnet-4.5-all for roleplay. Pretty much exactly what it says on the tin, the venerable C2 logs with the last turn regenerated by Sonnet 4.5 and refusals removed.
  • ConicCat/Gutenberg-SFT. A reformatted version of the original Gutenberg DPO dataset by jondurbin for SFT with some slight augmentation to address many of the samples being overly long.
  • A dataset of short story anthologies. Unfortunately, I am unable to release this set as all of the data is under copyright.