symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V10-dequantized

TEXT GENERATIONPricing:Input $0.4 / Cached $0.07 / Output $4Concurrent Unit Cost:3Model Size:35.1BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 27, 2026Architecture:Transformer Featherless Exclusive Cold

The symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V10-dequantized model is a 35.1 billion parameter language model based on the Qwen 3.6 architecture. It is a dequantized version of the LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V10-GGUF model, designed for deployment with the MLX library. This model offers a substantial parameter count for complex language understanding and generation tasks, with a context length of 32768 tokens.

Loading preview...

Model Overview

The symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V10-dequantized is a large language model with 35.1 billion parameters, built upon the Qwen 3.6 architecture. This specific version is a dequantized variant, derived from the LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V10-GGUF model, and is configured for use with the MLX library.

Key Characteristics

  • Architecture: Based on the robust Qwen 3.6 model family.
  • Parameter Count: Features 35.1 billion parameters, enabling sophisticated language processing capabilities.
  • Context Length: Supports a substantial context window of 32768 tokens, allowing for the processing of lengthy inputs and maintaining coherence over extended conversations or documents.
  • Deployment: Optimized for deployment using the MLX library, suggesting potential for efficient inference on Apple Silicon.

Potential Use Cases

This model is suitable for applications requiring advanced language understanding and generation, particularly where a large context window is beneficial. Its dequantized nature may offer improved precision for certain tasks. Developers looking to leverage a powerful Qwen-based model within the MLX ecosystem will find this model particularly relevant.

Finetunes
3 models