InferX Beta Serverless GPU Inference Platform, Built for Agent-Native Workloads

gemma-4-31B-it-uncensored-heretic

A 31B Gemma-4 model modified for reduced safety restrictions and more open responses
llmfan46 multimodal image2text reasoning coding chat

llmfan46/gemma-4-31B-it-uncensored-heretic is a fine-tuned variant of Gemma-4-31B-it, designed to reduce refusal behavior and safety filtering while preserving strong reasoning, coding, and conversational capabilities, making it suitable for research, roleplay, and advanced agent workflows that require fewer alignment constraints.

Log in to deploy: this public page shows the catalog model details, but deployment and customization stay behind login.
Log in to deploy

Metadata

Provider
llmfan46
Modality
multimodal
API type
image2text
Source
Created
2026-04-04 22:28:01 UTC
Updated
2026-04-20 18:42:02 UTC
Catalog version
8
Visibility
Published

Specifications

Parameters
MoE
No
Max model length
2000
Image
inferx/vllm-openai:gemma4_test1

Default Deploy Config

GPU count
1
vRAM
70000 MB
Summary
1xGPU 70000 MB

Recommended Use Cases

Model Spec