Qwen3.6 35B A3B nvfp4

Qwen3.6

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

Released April 2026context N/A35B params

A mid-sized mixture-of-experts model from the Qwen3.6 family, activating around 3 billion parameters per forward pass despite having 35 billion total. It handles both text and image inputs, making it multimodal out of the box. The nvfp4 quantization keeps memory footprint low, which may introduce minor quality trade-offs compared to full-precision variants.

Qwen3.6 35B A3B nvfp4

Qwen3.6

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

Released April 2026context N/A35B params

A mid-sized mixture-of-experts model from the Qwen3.6 family, activating around 3 billion parameters per forward pass despite having 35 billion total. It handles both text and image inputs, making it multimodal out of the box. The nvfp4 quantization keeps memory footprint low, which may introduce minor quality trade-offs compared to full-precision variants.

Glossary

Forward PassA single computation cycle where input data flows through the model's layers to produce an output prediction.Full-PrecisionA model using standard 32-bit floating-point numbers to represent weights, providing maximum accuracy but requiring more memory.Memory FootprintThe amount of RAM or storage space a model requires to run, which is critical for deployment on resource-constrained devices.MultimodalA model that can process and understand multiple types of input, such as both text and images.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.PrecisionThe level of numerical detail a model uses to represent its internal values; higher precision means more accurate calculations but requires more memory.QuantizationReducing a model's numerical precision (e.g., from 16-bit to 4-bit) to shrink memory usage and speed up inference.