RP Chat
Ratings reflect this model as run on Arli AI.
Gemma-4-31B-Scarlet-Shadow is a text generation model available on Arli AI. It offers 31B 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 ModelsInput (24H)
75K
Output (24H)
0
Input (7D)
792K
Output (7D)
17K
Typical Total Time
17.40s
Typical TTFT
2.77s
Typical Input TPS
1722.97
Typical Output TPS
17.45
Context Size
262144
Quantization
r128 on FP8
Engine
vllm
Creation Method
Merge
Model Class
Gemma-4-31B - LoRA
Chat Template
Gemma4
Reasoning
Yes
Vision
Yes
Parameters
31B
Added At
9/26/2026
Gemma-4-31B-Scarlet-Shadow is available through an OpenAI-compatible chat completions endpoint. Point any OpenAI SDK at https://api.arliai.com/v1, pass Gemma-4-31B-Scarlet-Shadow 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": "Gemma-4-31B-Scarlet-Shadow",
"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="Gemma-4-31B-Scarlet-Shadow",
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.
base_model:
Scarlet-Shadow-31B was created by merging Glimmering-Citrus-31B, Dark-Scarlett-v2.0-31B, gemma-4-31B-it-scotoma-2, and Gemma-4-31B-it using a custom method.
base_model: google/gemma-4-31B-it
models:
- model: Vortex5/Glimmering-Citrus-31B
- model: ReadyArt/Dark-Scarlett-v2.0-31B
- model: ReadyArt/gemma-4-31B-it-scotoma-2
merge_method: fcar
chat_template: auto
parameters:
strength: 1.0
gain: 0.5
focus: 0.55
recover: 0.25
distinct: 0.65
dtype: float32
out_dtype: bfloat16
tokenizer:
source: union
Character interaction, dialogue, personas, and multi-turn scenes.
Drafting fiction, descriptions, dialogue, and scene variations.
Short stories, longer narratives, plot development, and worldbuilding.
Generating concepts, outlines, alternatives, and writing ideas.