The Oracle
Chatting & How the AI Works 14 articles in this folder

Changing the AI model

Created by S G, Modified on Wed, Sep 23 at 5:54 PM by S G
  1. Open a chat with any character
  2. Open the three dots menu at the top right
  3. Select Generation Settings → Inference Model
  4. Select Change Model and pick from the models available on your tier

Models available on PixelChat:

ModelSize / contextAvailable on
PixelChat Default8B, 16KAll users
Zeta G4 26b26B, 16KAll users
Lyra Spiced8B, 16KAll users
Stheno8B, 8KAll users
Squelching Fantasies8B, 16KAll users
SpicedQ3 A3B30B, 16kAll users
Magnum 12B12B, 16KGet A Taste and above
Lyra 12B V412B, 16KTrue Supporter and above
Magnum Diamond24B, 16KTrue Supporter and above
Shimizu 24B24B, 16KTrue Supporter and above
Qwen3 235B235B, 16KTrue Supporter and above
Qwen3 235B Wildcard235B, 16KTrue Supporter and above
PixelXL132B, 16KI'm All In
Skyli ProPRO, 16KI'm All In
Qwen PlusPRO, 16KI'm All In
Glam 4.6355B, 32KI'm All In
Minimax456B, 16KI'm All In
DeepSeek V3671B, 32KI'm All In
DeepSeek V3 Wild Card671B, 32KI'm All In
Glam 5.1744b, 32KI'm All In
Kimi K21024B, 16KI'm All In
Deepseek V4 Pro1600B, 32KI'm All In

Each model has a short description of what it's best at. It's worth experimenting — models differ a lot in writing style, how well they follow instructions, and how prone they are to repetition.

Model availability depends on your tier. More detail: AI Models

Was this article helpful?

That’s Great!

Thank you for your feedback

Sorry! We couldn't be helpful

Thank you for your feedback

Let us know how can we improve this article!

Select at least one of the reasons
CAPTCHA verification is required.

Feedback sent

We appreciate your effort and will try to fix the article

Preview
0 of 0