Qwen3.8 Distill 35B A3B Coder Abliterated

Qwen3.6

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

Released August 2026262K context≈ 196,608 words

A coding-focused model built on Qwen3's architecture, distilled down to a 35B parameter count with only 3B active parameters via mixture-of-experts routing — meaning it punches above its weight in compute efficiency. The 'abliterated' variant has had refusal behaviors removed, making it more permissive in what it will generate. It handles a very large context window of 262K tokens, useful for working across large codebases.

Capabilities

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

Long Context

Exceptional

Instruction Following

Qwen3.8 Distill 35B A3B Coder Abliterated

Qwen3.6

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

Released August 2026262K context≈ 196,608 words

A coding-focused model built on Qwen3's architecture, distilled down to a 35B parameter count with only 3B active parameters via mixture-of-experts routing — meaning it punches above its weight in compute efficiency. The 'abliterated' variant has had refusal behaviors removed, making it more permissive in what it will generate. It handles a very large context window of 262K tokens, useful for working across large codebases.

Capabilities

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

Long Context

Exceptional

Instruction Following

Glossary

AbliteratedA model variant where safety filters and refusal mechanisms have been removed, allowing it to respond to requests without built-in content restrictions.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.Compute EfficiencyHow well a model performs relative to the computational resources (processing power and memory) required to run it.Context WindowThe maximum number of tokens a model can process in a single conversation or prompt.DistilledA model that has been compressed by training a smaller model to mimic a larger, more capable model, reducing size and computational requirements while retaining performance.Parameter CountThe total number of adjustable weights in a model; more parameters generally mean more capacity to learn, but also require more computing power.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.RoutingThe mechanism that decides which specialized sub-networks (experts) should process each input in a mixture-of-experts model.TokensThe basic units of text that a language model processes, typically representing words or word fragments.

Capabilities

Capabilities

Use Case Fit

Glossary