Qwen3.6 35B A3B uncensored heretic

Qwen 3

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released April 2026context N/A

A community-modified version of Qwen3's 35B mixture-of-experts architecture, with active parameters around 3B per forward pass. The 'uncensored heretic' label signals that safety filters and refusals have been stripped out, meaning it will engage with content that base models typically decline. This makes it more permissive but also means it operates without the guardrails the original model was trained with.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Creative Writing

Strong

Reasoning & Logic

Strong

Coding

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Qwen3.6 35B A3B uncensored heretic

Qwen 3

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released April 2026context N/A

A community-modified version of Qwen3's 35B mixture-of-experts architecture, with active parameters around 3B per forward pass. The 'uncensored heretic' label signals that safety filters and refusals have been stripped out, meaning it will engage with content that base models typically decline. This makes it more permissive but also means it operates without the guardrails the original model was trained with.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Creative Writing

Strong

Reasoning & Logic

Strong

Coding

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Glossary

Active ParametersThe subset of a model's total parameters that are actually used during inference for each input, as opposed to all parameters being used every time.ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.Forward PassA single computation cycle where input data flows through the model's layers to produce an output prediction.GuardrailsSafety mechanisms built into a model to refuse harmful requests or prevent it from generating unsafe content.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.Safety FiltersBuilt-in constraints that prevent a model from generating harmful, offensive, or inappropriate content in its responses.UncensoredA model without built-in safety filters or content restrictions, allowing it to generate responses on any topic without refusal.