---
title: Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp
canonical_url: "https://www.modelscope.ai/models/Shard/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp"
md_url: "https://www.modelscope.ai/models/Shard/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp.md"
repository: Shard/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp
last_updated: 2026-09-21
model_type:
  - qwen3_5_moe
architectures:
  - Qwen3_5MoeForConditionalGeneration
parameters: 5.1B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
downloads: 7
stars: 0
tags:
  - mlx
  - oq
  - quantized
---

# Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp

> Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp - An open-source model by Shard on ModelScope. Mirror of symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp from Hugging Face

- **Repository**: Shard/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp
- **Parameters**: 5.1B
- **Tags**: mlx, oq, quantized
- **Downloads**: 7
- **Stars**: 0
- **Last updated**: 2026-09-21

Source: https://www.modelscope.ai/models/Shard/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp

---

# Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V6-dequantized-oQ3e-mtp

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.5.4rc2) mixed-precision quantization.

## Quantization details

- **Model type**: qwen3_5_moe
- **Bits**: 3
- **Group size**: 64
- **Format**: MLX safetensors