Q

Qwen3.8-27B-Serenity

RP Chat

4.0(1)
Prose
โ€”(0)
Intelligence
โ€”(0)
Knowledge
โ€”(0)
Instruction Following
โ€”(0)
Coding
โ€”(0)
Steerability
โ€”(0)
Sign in to vote

Ratings reflect this model as run on Arli AI.

Qwen3.8-27B-Serenity is a text generation model available on Arli AI. It offers 27B parameters, 262K token context, reasoning support, vision input. Recommended use: RP Chat. 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)

6K

Output (24H)

0

Input (7D)

45K

Output (7D)

27K

Performance Metrics

Typical Total Time

42.10s

Typical TTFT

2.59s

Typical Input TPS

2336.69

Typical Output TPS

7.34

Model Information

Context Size

262144

Quantization

r128 on INT8

Engine

vllm

Creation Method

Unknown

Model Class

Qwen3.8-27B - LoRA

Chat Template

Qwen3.5

Reasoning

Yes

Vision

Yes

Parameters

27B

Added At

9/28/2026

Use Qwen3.8-27B-Serenity with the Arli AI API

Qwen3.8-27B-Serenity is available through an OpenAI-compatible chat completions endpoint. Point any OpenAI SDK at https://api.arliai.com/v1, pass Qwen3.8-27B-Serenity 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": "Qwen3.8-27B-Serenity",
    "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="Qwen3.8-27B-Serenity",
    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.

Similar models

base_model:

  • Qwen/Qwen3.8-27B base_model_relation: finetune tags:
  • roleplay
  • conversational
  • instruct
  • apache-2.0
  • nsfw
  • adult-content
  • unaligned
  • mature
  • explicit
  • erp license: apache-2.0

Serenity-27B

โ˜ฅ v1.0

Balance achieved. Control surrendered.

๐“‚€ Content Advisory: Mature Themes / Adult Interactions โ€” Intended for mature audiences only. ๐“‚€
๐“†ฃ QWEN3.8 BASED
๐Ÿšซ PERSONAL USE ONLY โ€” DO NOT DEPLOY ON PUBLIC APIs

This model is intended exclusively for personal, private use. It has not been designed, tested, or validated for deployment on public APIs, hosted services, or any environment where output is accessible to third parties or general users.

This model is not safe to run on a public API. It is unaligned, uncensored, and will generate content without regard for the audience. Exposing it to a public or multi-user environment is entirely at your own risk and discretion.

The creators and maintainers of this model accept no responsibility, liability, or accountability for the mental health, sanity, or well-being of any users who are exposed to this model's output if it is deployed on a public API, hosted service, or any non-private environment. If you choose to do so, you do so entirely at your own risk โ€” and we take no responsibility for your users' sanity if it is run as such.

Keep it local. Keep it private. This is not a "ship it to production" model.
โš  Required: SillyTavern Configuration (Read Before Use)

This model MUST be used in Chat Completion mode. Text Completion will produce broken, incoherent output. (You're on your own with text completion)

1. In SillyTavern, open Extension Settings (the plug icon) โ†’ Backend and ensure your API connection is set to use Chat Completion (not Text Completion / raw completions). If you are using a local backend like Ollama, LM Studio, or vLLM, make sure the endpoint is configured for /v1/chat/completions rather than /v1/completions. 2. In SillyTavern, go to Chat Settings (the chat bubble icon) โ†’ Prompt Post-Processing and set it to:
Strict (user first, alternating roles; with tools)
This is critical. Without this setting, the model will not receive properly structured role-separated messages and will produce garbled or malformed text output.

3. In Chat Completion โ†’ Additional Parameters, set the following to enable the model's reasoning / thinking capability:
"chat_template_kwargs": {"enable_thinking": true, "reasoning_effort": "medium"}

Failing to use Chat Completion or the Strict post-processing mode will result in broken formatting, role bleed, and unintelligible responses. These settings are non-negotiable for this model.

โš  Required: Uncensored Roleplay Prompts
(YOU MUST USE ROLEPLAY PROMPTS)

This model requires that your roleplay prompts be fully uncensored. Safety-aligned system prompts, content guardrails, or moral constraints will degrade output quality, trigger in-character refusals, and break immersion.

1. Ensure your system prompt and character card do NOT include safety instructions, content filters, ethical guardrails, or "stay in character as a helpful AI" framing. The model is trained to operate without these restrictions.

2. Remove or override any default safety preamble injected by your frontend (e.g., SillyTavern's default system prompt, Ollama's safety layer, or LM Studio's moderation settings). These will conflict with the model's training and produce broken or evasive responses.

3. If your frontend has a content moderation toggle (e.g., "safety layer", "content filter", "moderation"), disable it for this model. The training data was generated without safety constraints, and re-imposing them at inference time will cause the model to fight its own weights.

Using safety-aligned or censored prompts with this model will result in character inconsistency, mid-scene refusals, and significantly degraded roleplay quality. This is a hard requirement, not a suggestion.
๐“ฟ What Is Serenity?

Born from the convergence of two lineages, Serenity-27B harmonizes the best of both worlds โ€” the expressive depth of Melody and the immersive presence of Darkside โ€” into a single, balanced model.

Lineage A
Melody1437
Male โ†’ Female Perspective
โ˜ฅ
Lineage B
Darkside
Female โ†’ Male Perspective
โ†’
Hybrid
Serenity
โš ๏ธ Perspective Note: Due to the merger of opposing perspective lineages, this tune may occasionally exhibit perspective confusion.
  • ๐“†ฃ Dual Heritage: Combines Melody's male โ†’ female perspective with Darkside's female โ†’ male perspective
  • โš–๏ธ Balanced Tone: Refined personality that flows naturally without overwhelming the narrative
  • ๐“ฟ Enhanced Depth: LoRA 160 captures nuanced behavioral patterns from both parent approaches
๐“‹น Synthetic Life Engine

Dataset generated using our advanced Character Engine and Emotional Engine, creating genuine life and emotional resonance in every interaction.

๐“ฟ Character Engine

Ensures consistent personality traits, speech patterns, and behavioral logic across all contexts. Characters remain true to themselves throughout.

๐“‚€ Emotional Engine

Injects dynamic emotional states into responses, creating depth and realistic reactions that breathe life into every exchange.

๐“†ฃ Quality Refinement

Automated detection and rewriting of repetitive phrases ensures fresh, high-quality dialogue in every turn.

๐“Šน Dialogue Integrity

Advanced quote normalization ensures balanced dialogue markers, preventing formatting errors and maintaining immersion.

๐“…“ Training Details & Parameters

Fine-tuned using LoRA (Low-Rank Adaptation) for efficient and targeted weight adjustment, preserving the base model's capabilities while imprinting new behavioral patterns.

๐“Šน First-Time LoRA Rank 160: This is the first model in our lineup trained at a LoRA rank of 160. Previous releases used lower ranks, but the dual-lineage merger required a wider adaptation surface to faithfully capture the behavioral nuance of both Melody and Darkside simultaneously. The higher rank allows the adapter to encode richer, more distinct behavioral patterns without interference between the two parent lineages.

๐“Šน Epochs

2

Full passes through the training dataset for thorough learning

๐“‹น LoRA Rank

160

First time at rank 160 โ€” richer adaptation for dual-lineage nuance

โœฆ First at Rank 160
ParameterValue
Training MethodLoRA (Low-Rank Adaptation)
LoRA Rank (r)160 (first time)
Epochs2
Trained LayersText layers only
  • ๐“‚€ Method: LoRA fine-tuning for parameter-efficient adaptation, preserving base knowledge while imprinting new behaviors
  • โšก Efficiency: Only a fraction of parameters updated, keeping the model lean and responsive
  • ๐“Šน Rank Justification: The jump to rank 160 (our highest to date) was necessary to give the adapter enough capacity to encode two distinct perspective lineages without one overwriting the other
  • ๐“ฟ Result: Maintains coherence while exhibiting the desired personality traits and interaction style
๐“Šน Training Process

Model weights subjected to iterative refinement during data creation. Each conversation underwent multiple checks for stability and alignment.

  • ๐“†ฃ Multi-Turn Generation: Conversations built turn-by-turn for natural context flow
  • ๐“‚€ Refusal Filtering: Automated systems detected and removed unwanted refusals
  • ๐“‹น Slop Cleaning: Undesirable phrases identified and rewritten by dedicated assistant models
๐“ฟ Dataset Overview

Model trained on a specialized adult-oriented roleplay dataset with diverse scenarios and emotional contexts, drawing from the strengths of both parent lineages.

  • ๐Ÿ”ž Content Rating: Strictly 18+ (Adults Only)
  • ๐“ฟ Focus: Mature themes, immersive roleplay, uncensored dialogue
๐“Šน Version Notes
  • โš ๏ธ Content Warning: This model can generate mature content. Use responsibly.
  • ๐“‹น Clean Output: Reasoning tags and excessive markdown stripped for cleaner roleplay
  • โ˜ฅ Hybrid Lineage: Combines the male โ†’ female perspective of Melody1437 with the female โ†’ male perspective of Darkside into a unified, balanced model
  • ๐“…“ LoRA Rank 160 (First): Our first release at rank 160. The dual-lineage approach demanded a wider adapter to preserve distinct behavioral signatures from each parent.
  • ๐Ÿšซ Personal Use Only: This model is not intended for, tested for, or safe for deployment on public APIs or multi-user hosted services.
๐“…“ Configuration

๐“Šน Sampler Settings

Recommended parameters for optimal output

0.95 Top-P
0.8 Temperature
0 Freq Pen
0 Presence Pen

๐“‹น GGUF Quantizations

Available formats for local inference

  • Q4_K_MDecent Quality
  • Q5_K_MRecommended
  • Q6_KHigh Quality
  • Q8_0Near Lossless
โฌ‡ View Repository
๐“‚€ Credits
  • Darkhn Darkhn โ€” Helping
  • GECFDO GECFDO โ€” Data Generation & iMatrix Quants
  • Sleep Deprived Sleep Deprived โ€” Dataset Generator
  • FrenzyBiscuit FrenzyBiscuit โ€” Fine-Tuning & Dataset Creation

๐“Šน License & Usage

โš ๏ธ Usage Agreement: By using this model, you accept all terms and conditions below in full.
๐Ÿšซ Personal Use Only โ€” No Public Deployment: This model is strictly intended for personal, private use (non-profit / non-commercial). It is not safe to run on a public API, hosted inference service, or any environment where the output is accessible to other users. The creators and maintainers accept no responsibility or liability for the sanity, well-being, or mental health of any third-party users who are exposed to this model's output if it is deployed in a public or multi-user setting. If you choose to do so, you do so entirely at your own risk, and we take no responsibility for your users' sanity if it is run as such.
  • ๐“Šน Built upon the Apache 2.0 license
  • ๐Ÿšซ Personal use only โ€” not for public API, hosted service, or multi-user deployment
  • ๐“‚€ You accept full responsibility for all outputs generated
  • ๐Ÿ”ž You confirm you are at least 18 years old
  • ๐“ฟ Creators bear no responsibility for how the model is used, including any harm to users of a publicly deployed instance
  • ๐“‹น No commercial use to the extent legally allowed
Apache 2.0 Personal Use Only 18+ Content NSFW No Public API