Qwen3 235B A22B Instruct 2507

Alibaba's largest Qwen2.5 model featuring improved capabilities in coding, mathematics, and instruction following across more than 29 languages. With 72B parameters and 128K context support, it delivers top-tier performance for complex tasks requiring deep context understanding and sophisticated reasoning.

A versatile dense model offering powerful reasoning abilities paired with efficient dialogue processing. Developed by Alibaba, it supports extensive 32K context windows (extendable to 131K), features both thinking and non-thinking modes, and excels in coding, mathematics, and multilingual support across 119 languages and dialects.

A Mixture-of-Experts model that activates only 3.3B of its 30.5B parameters per forward pass. Offers dual thinking modes: a detailed step-by-step reasoning mode for complex problems and a faster non-thinking mode for simpler queries. Despite its small active parameter count, it outperforms QwQ-32B that has 10 times more activated parameters.

Qwen-Image is an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing. It supports parallel CFG and LoRA merging (up to 3 LoRAs), configurable inference steps, and an optional turbo mode for faster generation using optimized settings (10 steps, CFG=1.2).

Qwen Image 2512 is an improved version of Qwen Image with better text rendering, finer natural textures, and more realistic human generation. This 20B MMDiT model achieved top ranking among open-source models after 10,000 blind comparison rounds on AI Arena, released December 31, 2025, and is licensed under Apache 2.0.

Qwen-Image 3.0 is a general-purpose image generation and editing model that balances quality and speed. It excels at complex text rendering (multi-line, paragraph-level layouts), fine detail, and realistic textures, and supports both text-to-image (T2I) and image-to-image/editing (I2I) on DashScope's multimodal-generation endpoint.

Qwen-Image 3.0 Pro is the high-quality tier of the Qwen-Image 3.0 series, offering stronger text rendering, more realistic textures, and better semantic adherence for both text-to-image (T2I) and image-to-image/editing (I2I). Output resolution ranges from 512x512 up to 2048x2048 (PNG).

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

Qwen3-Coder-480B-A35B-Instruct is Qwen3's most agentic code model, with strong agentic coding and browser-use performance comparable to Claude Sonnet.

Qwen3-Embedding-8B is the largest model in the Qwen3 Embedding series, purpose-built for text embedding and retrieval tasks. It ranks No.1 on the MTEB multilingual leaderboard, supports 100+ languages, and produces embeddings up to 4096 dimensions with support for user-defined output dimensions (Matryoshka Representation Learning) from 32 to 4096. The model is instruction-aware, allowing custom task instructions to be prepended to inputs for improved retrieval performance, and supports a 32K token context length.

Qwen3-Next is a next-generation foundation model architecture focused on scaling efficiency for both total parameters and context length.

Qwen3-VL is the most powerful vision-language model in the Qwen series, with upgrades in text understanding, visual perception and reasoning, longer context, spatial and video comprehension, and agent interaction.

Qwen3-VL 30B A3B is a compact vision-language MoE model in the Qwen3-VL series with strong visual perception, reasoning and agent capabilities.

Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model with a 262K context window (extensible to 1M), thinking mode, tool calling, multi-token prediction and 201 languages.

Qwen3.5-35B-A3B is an efficient MoE model (35B total, 3B active) with a 262K context window, thinking mode, tool calling and 201 languages.

Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 MoE model (397B total, 17B active) with a 262K context window, thinking mode, tool calling and support for 201 languages.

Qwen3.5-9B uses a hybrid Gated Delta Networks and sparse MoE architecture with a 262K context window, thinking mode, tool calling and multi-token prediction.

Qwen3.6-27B is a dense 27B model from the Qwen3.6 series for coding and general-purpose reasoning.

Qwen3.6-35B-A3B is Alibaba's Mixture-of-Experts model with 35B total and 3B active parameters (256 experts), prioritizing stability and real-world utility for coding.

Qwen3.7-Max is the largest and most capable model in the Qwen3.7 series, a next-generation flagship designed for agent-centric work.

Qwen3.8-Flash is Qwen's fast, low-cost model with a one-million-token context window, billed at a flat rate across the entire window.