Glossary
Qwen
Alibaba's open-weight model family, leading the multilingual and Chinese-language open-weight space, released under Apache 2.0 with sizes from 0.6B to 235B parameters.
Alibaba’s open release line, one of the more prolific open weightsweightsA model release that publishes the trained parameters under some downloadable license, distinct from "open source" which (per OSAID) also requires data and training-code openness. Open full entry families in 2024 to 2026. Qwen3 (April 2025) shipped six dense sizes (0.6B, 1.7B, 4B, 8B, 14B, 32B) and two MoE variants (30B-A3B and 235B-A22B), all under Apache 2.0governanceA permissive open-source license used by most open-weight model releases (Llama from 4 onward partial, Qwen, Mistral, DeepSeek, Falcon), allowing commercial use without acceptable-use restrictions. Open full entry . The 235B-A22B mixture of expertsweightsA model architecture where each token activates only a fraction of total parameters by routing through learned expert subnetworks, decoupling capacity from compute. Open full entry flagship landed near the top of open weightsweightsA model release that publishes the trained parameters under some downloadable license, distinct from "open source" which (per OSAID) also requires data and training-code openness. Open full entry benchmarks at release.
The breadth of the catalog is the differentiator: a team can pick a Qwen of the right size for any deployment from on-devicesovereignty-decentralizationRunning model inference on the user's local hardware (phone, laptop, embedded device), enabled by smaller models, FP8 quantization, and runtimes like llama.cpp and MLX. Open full entry through frontierweightsThe current capability envelope of AI, defined by the most capable models in deployment at any given time; an evolving label rather than a fixed threshold. Open full entry -class, with consistent training data, license, and tokenizerdataThe component that splits raw text into discrete units (tokens) the model can process, usually using a learned subword vocabulary like Byte-Pair Encoding. Open full entry . Multilingual coverage is unusually strong, particularly for Chinese.
Full coverage at /projects/qwen.