DavidAU/Gemma3-27B-it-vl-GLM-4.7-Uncensored-Heretic-Deep-Reasoning
TEXT GENERATIONConcurrency Cost:2Model Size:27BQuant:FP8Ctx Length:32kPublished:Jan 26, 2026License:apache-2.0 Vision Architecture:Transformer0.0K Open Weights Warm

DavidAU/Gemma3-27B-it-vl-GLM-4.7-Uncensored-Heretic-Deep-Reasoning is a 27 billion parameter Gemma 3 instruction-tuned model, fine-tuned with the GLM 4.7 reasoning dataset via Unsloth. This model features 128k context and is fully uncensored, excelling in deep reasoning and image intelligence. It is optimized for direct, detailed responses across various tasks, including those requiring explicit content, and shows improved benchmarks over its non-thinking counterpart.

Loading preview...

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p