symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-dequantized

TEXT GENERATIONPricing:Input $0.4 / Cached $0.07 / Output $4Concurrent Unit Cost:3Model Size:35.1BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 3, 2026Architecture:Transformer Featherless Exclusive Cold

symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-dequantized is a 35.1 billion parameter language model, dequantized from the LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-GGUF base model. This model is designed for general language generation tasks, leveraging its large parameter count and uncensored nature for broad applicability. It is suitable for developers seeking a powerful, adaptable model for various text-based applications.

Loading preview...

Model Overview

symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-dequantized is a substantial 35.1 billion parameter language model. It is a dequantized version derived from the LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-GGUF base model, indicating a focus on restoring precision from a quantized format.

Key Characteristics

  • Parameter Count: Features 35.1 billion parameters, placing it in the large-scale LLM category.
  • Base Model Lineage: Built upon the Qwen3.6 architecture, specifically from a variant that includes "Uncensored," "Genesis," and "Hermes" fine-tuning elements, suggesting a broad and potentially less restrictive response generation capability.
  • Dequantized Format: The model has been dequantized, which typically means it offers higher precision compared to its quantized GGUF source, potentially leading to improved performance and fidelity in outputs.

Potential Use Cases

  • General Text Generation: Suitable for a wide array of tasks including content creation, summarization, and conversational AI.
  • Research and Development: Its dequantized nature and large parameter count make it a strong candidate for further fine-tuning or experimental applications where precision is valued.
  • Applications Requiring Unrestricted Output: The "Uncensored" aspect implies it may be used in scenarios where less filtered or more direct responses are desired, though users should exercise caution and responsibility.