RP Chat
Ratings reflect this model as run on Arli AI.
Gemma-4-31B-Artemis-31B-v1 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)
9K
Output (24H)
4K
Input (7D)
20K
Output (7D)
32K
Typical Total Time
24.08s
Typical TTFT
3.48s
Typical Input TPS
1506.03
Typical Output TPS
16.57
Context Size
262144
Quantization
r128 on FP8
Engine
vllm
Creation Method
Finetune
Model Class
Gemma-4-31B - LoRA
Chat Template
Gemma4
Reasoning
Yes
Vision
Yes
Parameters
31B
Added At
10/1/2026
Gemma-4-31B-Artemis-31B-v1 is available through an OpenAI-compatible chat completions endpoint. Point any OpenAI SDK at https://api.arliai.com/v1, pass Gemma-4-31B-Artemis-31B-v1 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-Artemis-31B-v1",
"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-Artemis-31B-v1",
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:
Hi! I'm Drummer. I'm a Software Engineer with experience in JavaScript, Golang, Python, and generally engineering the crap out of things.
Why I'm in the AI space:
I started my tuning venture back in mid-2024 when I wanted to improve its literary capabilities. I've come a long way since then and I have branched out and specialized. Foundational models today are optimized for non-creative uses, and I believe there is a place for AI in creativity and entertainment.
I am here to take the road less traveled by.
Bottomline: My models are usually geared towards creativity, usability, and entertainment!
While intelligence, correctness, and problem solving are not my priority, they are still one of many qualities I want in my models.
The primary goal is to enhance the experience for users looking to use models for creative uses, and other use cases which require no alignment.
In an effort to make it clear to myself and to others what I'm aiming for, I've identified certain qualities that my users often want:
Creativity
(Dis)alignment
Intelligence
If it doesn't excel in one of these qualities, or if it's overall mediocre for its size, then I would most likely reiterate until I get something right.
A person is defined by the language they use. Not whether they speak in English or German, but in how they perceive reality.
Just like how we associate a serial killer as a mind that can't map 'murder' to 'evil', an innocent person is a mind that simply can't imagine 'murder'. They get confused when forced to deal with such subjects.
AI's use of language speaks volumes about their 'perception' of reality. If a language model has been skewed and limited to a positive perception, then it's ability to imagine is also limited.
Finetuning is an opportunity to adjust and broaden the language. Corporations use it to achieve safety and compliance. I'm here to
Drummer proudly presents...

The v1 release was overdue. It was a good early attempt that pulled out the best writing potential in Gemma 4. However, v1 might require some handholding, token banning, etc., for stability and to avoid dash spiraling. With that said, many fans still vouched for [what is now] v1.
The v1.1 release addresses the issues of v1 while retaining as much of the charm that v1 had.
What's next for 31B? More iterations, of course! More data, more sophisticated training configurations, and even an upscale!
Running it without thinking with a kind of a complex scenario and it's looking great compared to vanilla G4. It's very keen on slow burn and the outputs are pretty smart and logical. Not seeing any overtly bubbly rhetoric and it doesn't yap as much.
Cant stop saying it, an absolutely beautiful model. Had a 30 minute crying spell from a RP. it was beautiful, devastating, and everything in between 10/10
wow. it performs very well. Its my new favorite model. I am using the Q6 with Kobold and now tested this Buun llama cpp on turbo3_tcq. Works fine.
config-v1h