Qwen3.5 122B A10B int4 fp8 hybrid

Qwen 3

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

Released June 2026context N/A

A large mixture-of-experts model from the Qwen 3 family, published by bleysg in a quantized hybrid format combining int4 and fp8 precision. The quantization approach trades some numerical fidelity for reduced memory footprint, activating around 10 billion parameters per forward pass despite a 122 billion total parameter count. Behavior and capability details beyond its architecture and format are not well documented.

Capabilities

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

Reasoning & Logic

Strong

Multilingual

Strong

Coding

Use Case Fit

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

Qwen3.5 122B A10B int4 fp8 hybrid

Qwen 3

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

Released June 2026context N/A

A large mixture-of-experts model from the Qwen 3 family, published by bleysg in a quantized hybrid format combining int4 and fp8 precision. The quantization approach trades some numerical fidelity for reduced memory footprint, activating around 10 billion parameters per forward pass despite a 122 billion total parameter count. Behavior and capability details beyond its architecture and format are not well documented.

Capabilities

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

Reasoning & Logic

Strong

Multilingual

Strong

Coding

Use Case Fit

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

Glossary

ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.FP8 PrecisionA data format that stores numbers using 8 bits instead of the standard 32 bits, significantly reducing memory requirements with minimal quality loss.FidelityThe degree to which a quantized or compressed model preserves the quality and accuracy of the original full-precision model.Forward PassA single computation cycle where input data flows through the model's layers to produce an output prediction.Memory FootprintThe amount of RAM or storage space a model requires to run, which is critical for deployment on resource-constrained devices.Numerical FidelityThe accuracy and precision with which a model preserves mathematical calculations; lower fidelity means some precision is lost, often as a trade-off for smaller model size.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.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.QuantizedA technique that reduces a model's size and memory usage by storing weights with lower precision (fewer bits), trading some accuracy for efficiency.