Alibaba Qwen models
Alibaba's Qwen team builds the Qwen (Tongyi Qianwen) language, vision, audio, and image model families, along with the related Wan video generation models.
Hangzhou, ChinaFounded 1999qwen.ai
- Releases
- 84
- Open weights
- 60
- Latest
- Nov 16, 2026
November 2026
2 releasesQwen4-Max
Qwen4-Max is the first model of Alibaba's Qwen4 generation, a sparse mixture-of-experts flagship with native vision and a 1M-token context, aimed at long-running professional, coding, and agent work.
- Modalities
- text, image, video → text
- Context
- 1M context
- Parameters
- MoE: 2.4T total, 71B active, plus 328B N-gram embedding parameters
- At launch
- API, Consumer app
- API model ID qwen4-max on QwenCloud through the Token Plan or the API, and usable in Qwen Studio, QwenWork, and Qoder at launch
- New architecture combining Gated DeltaNet, Qwen Sparse Attention, gated residuals, and N-gram embeddings
- Qwen reported a Work360 score of 52.69, up from 47.74 for Qwen3.8-Max, and said it lowered API prices from that model
- Qwen said smaller models in the Qwen4 family would follow as open weights
Qwen4-Max-Preview
Qwen4-Max-Preview was a time-limited preview of Alibaba's first Qwen4 flagship, offered through Model Studio's Token Plan subscription ahead of the production Qwen4-Max. It reads text, images, and video and targets coding, office work, frontend design, and agentic tasks.
- Modalities
- text, image, video → text
- Context
- 1M context
- At launch
- API
- API model ID qwen4-max-preview, offered only through Token Plan Personal and Team, without pay-as-you-go access
- Alibaba scheduled the preview from November 11 to November 25, 2026 (UTC+8) and said the model would be retired afterward
- 1M-token context and up to 393,216 output tokens shared between thinking and the answer
- Thinking on by default, with low, medium, and xhigh reasoning effort; followed by Qwen4-Max on November 16, 2026
September 2026
2 releasesQwen-Image-2.1
Qwen-Image-2.1 is an open-weights Qwen image model that unifies text-to-image generation and image editing in a single model. It is designed to balance generation quality, inference efficiency, and cost, and natively supports transparent images.
- Modalities
- text, image → image
- Parameters
- 7B (visual generation component)
- License
- Qwen Research License Agreement
- At launch
- API, Open weights
- Visual generation component has 32 single-stream DiT layers and 7B parameters
- Qwen-Image-2.1-Turbo, which needs only 8 denoising steps, followed on October 9, 2026
- Pro and Turbo APIs went live on Alibaba Cloud Model Studio on October 9, 2026
Qwen3.8-Omni-Flash
Qwen3.8-Omni-Flash is Qwen's omni-modal model for real-time audio-visual interaction and agentic delivery. It accepts text, image, audio, and video input with a 1M-token context window.
- Modalities
- text, image, audio, video → text, audio
- Context
- 1M context
- At launch
- API
- Qwen reports text performance comparable to a text-only model of the same size
- Upgraded video captioning lets users set subject, time range, detail, and format
August 2026
4 releasesQwen3.8-Flash-Next
Qwen3.8-Flash-Next is an open-weights multimodal mixture-of-experts model that previews the architecture planned for Qwen4. It combines Gated DeltaNet with Qwen Sparse Attention and adds Gated Residual and N-gram Embedding.
- Modalities
- text, image → text
- Context
- 256K context
- Parameters
- MoE: 125B total, 6B active, plus 51B n-gram embedding
- License
- Qwen Community License 1.0
- At launch
- Open weights
- Native 262,144-token context, extensible to 1,000,000 tokens with YaRN
- Qwen says training cost about 1/9 of Qwen3.7-Plus
- Weights on Hugging Face and ModelScope under the Qwen Community License 1.0
Qwen3.8-27B
Qwen3.8-27B is a dense 27B open-weights model in the Qwen3.8 series, released on Hugging Face and ModelScope after Qwen3.8-Max. It is a causal language model with a vision encoder.
- Modalities
- text, image → text
- Context
- 256K context
- Parameters
- 27B
- License
- Apache-2.0
- At launch
- Open weights
- Native 262,144-token context, extensible to 1,000,000 tokens
- Released under the Apache 2.0 license
- Follows the Qwen3.8-2.4T-A95B open-weights release on August 12, 2026
Wan-Animate-2
Wan-Animate-2 is an end-to-end character animation model that directly consumes driving videos in a redesigned Diffusion Transformer. It targets high-fidelity motion and strong identity preservation.
- Modalities
- text, image, video → video
- Parameters
- 14B
- License
- Apache-2.0
- At launch
- Open weights
- Released as Base and Distillation weights on August 7, 2026
- Published on Hugging Face as Wan2.2-Animate-2-14B
- Released under the Apache 2.0 license
Qwen3.8-Max
Qwen3.8-Max is the most capable model in Alibaba's Qwen family to date, built on the Qwen3.5 architecture for coding, work, research, and long-horizon tasks. It is the first Qwen-Max-class model with open weights.
- Modalities
- text → text
- Context
- 256K context
- Parameters
- MoE: 2.4T total, 95B active
- License
- Qwen3.8-Max License
- At launch
- API, Open weights
- Weights published as Qwen3.8-2.4T-A95B on Hugging Face and ModelScope on August 12, 2026
- Native 262,144-token context, extensible to about 1M tokens
- API available on QwenCloud at launch
July 2026
1 releaseQwen-Image-3.0
Qwen-Image-3.0 is the third-generation foundational image generation model in the Qwen-Image series. Qwen centers it on realism, with richer content, authentic details, and deeper knowledge.
- Modalities
- text, image → image
- At launch
- Consumer app
- Supports up to 4.5K tokens of input for complex layouts such as newspapers and storyboards
- Available to try on Qwen Chat
- Successor to Qwen-Image-2.0
June 2026
1 releaseQwen3.7-Plus
Qwen3.7-Plus is a multimodal agent model that unifies vision and language, building on the Qwen3.7 text backbone. It can read screens, operate GUIs, write code from visual references, and navigate mobile apps.
- Modalities
- text, image, video → text
- At launch
- API
- Accepts text, image, and video input
- Supports preserving thinking content across turns for agentic tasks
- Available through Alibaba Cloud Model Studio
May 2026
1 releaseQwen3.7-Max
Qwen3.7-Max is Qwen's proprietary model designed for the agent era, targeting coding, office workflow automation, and long autonomous runs. Qwen demonstrated a 35-hour autonomous kernel optimization run with more than 1,000 tool calls.
- Modalities
- text → text
- At launch
- API
- Built to work across scaffolds such as Claude Code, OpenClaw, and Qwen Code
- Supports MCP integrations and multi-agent orchestration
- Available through Alibaba Cloud Model Studio
April 2026
4 releasesQwen3.6-27B
Qwen3.6-27B is a dense 27B open-weights multimodal model focused on agentic coding. Qwen says it surpasses the previous open flagship, Qwen3.5-397B-A17B, on major coding benchmarks while being simpler to deploy.
- Modalities
- text, image → text
- Context
- 256K context
- Parameters
- 27B
- License
- Apache-2.0
- At launch
- Consumer app, Open weights
- Supports multimodal thinking and non-thinking modes
- Native 262,144-token context, extensible to 1,010,000 tokens
- Available on Qwen Studio; weights under the Apache 2.0 license
Qwen3.6-Max-Preview
Qwen3.6-Max-Preview is an early preview of Qwen's next proprietary flagship, released after Qwen3.6-Plus. It brings stronger world knowledge, instruction following, and agentic coding than Qwen3.6-Plus.
- Modalities
- text → text
- At launch
- API, Consumer app
- Available on Qwen Studio
- API model name qwen3.6-max-preview on Alibaba Cloud Model Studio
- Qwen describes it as still under active development
Qwen3.6-35B-A3B
Qwen3.6-35B-A3B is a sparse open-weights mixture-of-experts model focused on agentic coding, surpassing Qwen3.5-35B-A3B by a wide margin. It supports multimodal thinking and non-thinking modes.
- Modalities
- text, image → text
- Context
- 256K context
- Parameters
- MoE: 35B total, 3B active
- License
- Apache-2.0
- At launch
- API, Consumer app, Open weights
- Offered on the Model Studio API as Qwen3.6-Flash
- Native 262,144-token context, extensible to 1,010,000 tokens
- Weights on Hugging Face and ModelScope under the Apache 2.0 license
Qwen3.6-Plus
Qwen3.6-Plus is Qwen's hosted model that succeeded Qwen3.5-Plus, with major upgrades to agentic coding from front-end work to repository-level tasks. It also improves multimodal perception and reasoning.
- Modalities
- text, image → text
- Context
- 1M context
- At launch
- API
- 1M-token context window by default
- Addresses community feedback from the Qwen3.5-Plus deployment
- Available through Alibaba Cloud Model Studio
March 2026
2 releasesQwen3.5-Omni
Qwen3.5-Omni is Qwen's omni-modal model series in Plus, Flash, and Light sizes, using a Thinker-Talker design for text and speech output. It adds semantic interruption, voice cloning, and coding from audio-visual instructions.
- Modalities
- text, image, audio, video → text, audio
- Context
- 250K context
- At launch
- API
- Supports 256K long-context input
- Available through the Offline API and the Realtime API
- Talker generates contextual speech from the Thinker's outputs
Qwen3.5 small models
The Qwen3.5 small models are four compact open-weights models, Qwen3.5-9B, 4B, 2B, and 0.8B, completing the Qwen3.5 lineup. Like the rest of the series, they are causal language models with a vision encoder.
- Modalities
- text, image → text
- Context
- 256K context
- Parameters
- 0.8B, 2B, 4B, 9B
- License
- Apache-2.0
- At launch
- Open weights
- Native 262,144-token context, extensible to 1,010,000 tokens
- Base checkpoints released alongside the instruct models
- Weights on Hugging Face and ModelScope under the Apache 2.0 license
February 2026
4 releasesQwen3.5 medium models
The Qwen3.5 medium models are Qwen3.5-122B-A10B, Qwen3.5-35B-A3B, and the dense Qwen3.5-27B, released after the flagship Qwen3.5-397B-A17B. They share the Qwen3.5 hybrid architecture with native vision.
- Modalities
- text, image → text
- Context
- 256K context
- Parameters
- MoE: 122B total, 10B active; MoE: 35B total, 3B active; 27B dense
- License
- Apache-2.0
- At launch
- Open weights
- Native 262,144-token context, extensible to 1,010,000 tokens
- Qwen3.5-35B-A3B also released as a base model
- Weights under the Apache 2.0 license
Qwen3.5
Qwen3.5 is Alibaba's model series that opened with the open-weights Qwen3.5-397B-A17B, a native vision-language model. It uses a hybrid architecture that combines linear attention through Gated Delta Networks with a sparse mixture-of-experts design.
- Modalities
- text, image, video → text
- Context
- 256K context
- Parameters
- MoE: 397B total, 17B active
- License
- Apache-2.0
- At launch
- API, Consumer app, Open weights
- Native 262,144-token context, extensible to 1,010,000 tokens
- Language and dialect support expanded from 119 to 201
- Hosted Qwen3.5-Plus offers a 1M context window by default with built-in tools
- Weights under the Apache 2.0 license
Qwen-Image-2.0
Qwen-Image-2.0 is Qwen's next-generation foundational image generation model, unifying image generation and editing in a single mode. It targets professional typography such as infographics, slides, posters, and comics.
- Modalities
- text, image → image
- At launch
- Consumer app
- Supports 1K-token instructions
- Native 2K resolution
- Smaller model size with faster inference than its predecessor; available on Qwen Chat
Qwen3-Coder-Next
Qwen3-Coder-Next is an open-weights model designed for coding agents and local development, built on Qwen3-Next-80B-A3B-Base. It was agentically trained at scale with executable task synthesis, environment interaction, and reinforcement learning.
- Modalities
- text → text
- Context
- 256K context
- Parameters
- MoE: 80B total, 3B active
- License
- Apache-2.0
- At launch
- Open weights
- Hybrid attention and mixture-of-experts architecture from Qwen3-Next
- 262,144-token native context
- Weights under the Apache 2.0 license
January 2026
4 releasesQwen3-ASR
Qwen3-ASR is an open-weights speech recognition family of Qwen3-ASR-1.7B and Qwen3-ASR-0.6B, released with the non-autoregressive Qwen3-ForcedAligner-0.6B. The models build on the audio understanding of Qwen3-Omni.
- Modalities
- audio → text
- Parameters
- 0.6B, 1.7B
- License
- Apache-2.0
- At launch
- Open weights
- Language identification and recognition for 52 languages and accents
- Qwen3-ForcedAligner-0.6B performs speech forced alignment
- Weights under the Apache 2.0 license
Qwen3-Max-Thinking
Qwen3-Max-Thinking is Qwen's flagship reasoning model, built by scaling model parameters and reinforcement learning compute on Qwen3-Max. It adds adaptive tool use for on-demand retrieval and code interpreter calls.
- Modalities
- text → text
- At launch
- API, Consumer app
- Available in Qwen Chat and through the Alibaba Cloud API
- Uses test-time scaling techniques to improve reasoning
- Improves factual knowledge, instruction following, and agent capabilities
Qwen3-TTS
Qwen3-TTS is Qwen's open-weights speech generation family supporting voice cloning, voice design, and natural-language voice control. It is built on the Qwen3-TTS-Tokenizer-12Hz multi-codebook speech encoder.
- Modalities
- text, audio → audio
- Parameters
- 0.6B, 1.7B
- License
- Apache-2.0
- At launch
- Open weights
- Released in 1.7B and 0.6B sizes
- Supports 10 major languages plus various dialects
- Weights under the Apache 2.0 license
Qwen3-VL-Embedding and Qwen3-VL-Reranker
Qwen3-VL-Embedding and Qwen3-VL-Reranker are open-weights multimodal retrieval models built on Qwen3-VL. They handle text, images, screenshots, and video in one framework for embedding and reranking.
- Modalities
- text, image, video → text
- Context
- 32K context
- Parameters
- 2B, 8B
- License
- Apache-2.0
- At launch
- Open weights
- Supports more than 30 languages
- Flexible embedding dimensions and customizable instructions
- Released in 2B and 8B sizes under the Apache 2.0 license
December 2025
3 releasesQwen-Image-2512
Qwen-Image-2512 is the December 2025 update of Qwen-Image's text-to-image foundation model. Qwen says it reduces the AI-generated look, improves realism for human subjects, and renders finer natural detail.
- Modalities
- text → image
- Parameters
- 20B
- License
- Apache-2.0
- At launch
- Consumer app, Open weights
- Weights on Hugging Face and ModelScope on release day
- Available to try on Qwen Chat
- Released under the Apache 2.0 license
Qwen-Image-Edit-2511
Qwen-Image-Edit-2511 is an enhanced version of Qwen-Image-Edit-2509 with better consistency. It mitigates image drift and improves character consistency in edits.
- Modalities
- text, image → image
- Parameters
- 20B
- License
- Apache-2.0
- At launch
- Consumer app, Open weights
- Available through the Image Editing feature on Qwen Chat
- Weights on Hugging Face and ModelScope
- Released under the Apache 2.0 license
Qwen-Image-Layered
Qwen-Image-Layered is a Qwen model that decomposes an image into multiple RGBA layers, so each layer can be edited independently. The layered output supports resizing, repositioning, and recoloring without affecting other content.
- Modalities
- text, image → image
- License
- Apache-2.0
- At launch
- Open weights
- Weights on Hugging Face and ModelScope
- Research paper published December 18, 2025
- Released under the Apache 2.0 license
September 2025
10 releasesQwen3-Max
Qwen3-Max is Alibaba's largest Qwen model at launch, with more than 1 trillion parameters pre-trained on 36T tokens. The official release followed a preview and improved coding and agent capabilities.
- Modalities
- text → text
- Parameters
- MoE: over 1T total
- At launch
- API, Consumer app
- Qwen3-Max-Instruct available via the Alibaba Cloud API and Qwen Chat
- Trained with a 1M-token context using the ChunkFlow strategy
- A Thinking variant was still in training at launch
Qwen-Image-Edit-2509
Qwen-Image-Edit-2509 is the September 2025 monthly iteration of the open-weights Qwen-Image-Edit model, adding support for multi-image input and improving consistency in edits compared with the August release.
- Modalities
- text, image → image
- Parameters
- 20B
- License
- Apache-2.0
- At launch
- Consumer app, Open weights
- Multi-image editing support
- Available through the Image Editing feature on Qwen Chat
- Weights under the Apache 2.0 license
Qwen3-LiveTranslate-Flash
Qwen3-LiveTranslate-Flash is Qwen's real-time multilingual audio and video interpretation model built on Qwen3-Omni. It supports offline and live translation in 18 languages and uses visual context to improve translations.
- Modalities
- audio, video → text, audio
- At launch
- API
- First Qwen interpretation model with visual context augmentation
- Trained on millions of hours of multimodal data
- Later followed by Qwen3.5-LiveTranslate-Flash and Qwen3.8-LiveTranslate
Qwen3-VL
Qwen3-VL is Qwen's vision-language series, opened with Qwen3-VL-235B-A22B in Instruct and Thinking versions. Qwen says its text performance matches the flagship Qwen3-235B-A22B-2507 language model.
- Modalities
- text, image, video → text
- Context
- 250K context
- Parameters
- MoE: 235B total, 22B active (flagship)
- License
- Apache-2.0
- At launch
- API, Consumer app, Open weights
- Native 256K-token context, expandable to 1M tokens
- OCR expanded to 32 languages from 10
- 30B-A3B followed October 4, 4B and 8B on October 15, and 2B and 32B on October 21, 2025
Qwen3Guard
Qwen3Guard is the first safety guardrail model series in the Qwen family, built on Qwen3 and fine-tuned for safety classification. It includes Qwen3Guard-Gen and Qwen3Guard-Stream, which detects unsafe content in real time during generation.
- Modalities
- text → text
- Parameters
- 0.6B, 4B, 8B
- License
- Apache-2.0
- At launch
- Open weights
- Both variants come in 0.6B, 4B, and 8B sizes
- Stream variant enables token-level streaming safety detection
- Weights under the Apache 2.0 license
Qwen3-Omni
Qwen3-Omni is Qwen's natively end-to-end multilingual omni-modal model, processing text, images, audio, and video and responding in real time with text and natural speech. It was released as Instruct, Thinking, and Captioner models.
- Modalities
- text, image, audio, video → text, audio
- Parameters
- MoE: 30B total, 3B active
- License
- Apache-2.0
- At launch
- API, Open weights
- Text interaction in 119 languages, speech understanding in 19, and speech generation in 10
- Qwen3-Omni-30B-A3B-Captioner is an open audio captioning model
- Weights under the Apache 2.0 license
Qwen3-TTS-Flash
Qwen3-TTS-Flash is Qwen's flagship text-to-speech model on the Qwen API, supporting multi-timbre, multilingual, and multi-dialect speech synthesis. It aims to produce natural and expressive speech.
- Modalities
- text → audio
- At launch
- API
- 17 voices, each supporting 10 languages
- Dialects including Hokkien, Wu, Cantonese, and Sichuanese
- Available through the Qwen API on Alibaba Cloud Model Studio
Wan2.2-Animate-14B
Wan2.2-Animate-14B is a unified model for character animation and replacement that replicates full-body movement and facial expression from a reference video.
- Modalities
- text, image, video → video
- Parameters
- 14B
- License
- Apache-2.0
- At launch
- Open weights
- Model weights and inference code released
- Diffusers integration added November 13, 2025
- Released under the Apache 2.0 license
Qwen3-Next
Qwen3-Next is a new Qwen architecture for training and inference efficiency, launched with Qwen3-Next-80B-A3B in Instruct and Thinking versions. It combines hybrid attention with an ultra-sparse mixture-of-experts design.
- Modalities
- text → text
- Context
- 256K context
- Parameters
- MoE: 80B total, 3B active
- License
- Apache-2.0
- At launch
- API, Open weights
- Base model matches dense Qwen3-32B at under 10% of its training cost, per Qwen
- More than 10 times higher throughput at contexts over 32K tokens
- Native 262,144-token context, extensible to 1,010,000 tokens
Qwen3-ASR-Flash
Qwen3-ASR-Flash is a speech recognition service built on Qwen3-Omni and tens of millions of hours of speech data. It supports 11 languages and multiple accents and accepts text context to customize results.
- Modalities
- audio → text
- At launch
- API
- Handles singing voice recognition
- Users can prompt with context in any format for customized transcription
- Offered as an API service
August 2025
3 releasesWan2.2-S2V-14B
Wan2.2-S2V-14B is an audio-driven cinematic video generation model in the Wan2.2 family that generates video from speech and a reference image.
- Modalities
- text, image, audio → video
- Parameters
- 14B
- License
- Apache-2.0
- At launch
- Open weights
- Supports 480P and 720P output
- Text-to-speech support through CosyVoice added September 5, 2025
- Released under the Apache 2.0 license
Qwen-Image-Edit
Qwen-Image-Edit is an image editing model built on the 20B Qwen-Image model, extending its text rendering to precise text editing in images. It feeds the input image to Qwen2.5-VL and a VAE encoder for both semantic and appearance editing.
- Modalities
- text, image → image
- Parameters
- 20B
- License
- Apache-2.0
- At launch
- Consumer app, Open weights
- Available through the Image Editing feature on Qwen Chat
- Weights on Hugging Face and ModelScope
- Released under the Apache 2.0 license
Qwen-Image
Qwen-Image is a 20B MMDiT image foundation model with significant advances in complex text rendering and precise image editing. It renders both alphabetic and logographic text, including English and Chinese.
- Modalities
- text → image
- Parameters
- 20B
- License
- Apache-2.0
- At launch
- Consumer app, Open weights
- Weights on Hugging Face and ModelScope at launch
- Image Generation available on Qwen Chat
- Released under the Apache 2.0 license
July 2025
5 releasesWan2.2
Wan2.2 is the open video generation family from Alibaba's Wan team, adding mixture-of-experts text-to-video and image-to-video models and a compact 5B text-and-image-to-video model.
- Modalities
- text, image → video
- Parameters
- MoE: A14B (T2V, I2V); 5B (TI2V)
- License
- Apache-2.0
- At launch
- Open weights
- T2V-A14B and I2V-A14B support 480P and 720P
- TI2V-5B uses a high-compression VAE and supports 720P
- Integrated into Diffusers and ComfyUI at launch; Apache 2.0 license
Qwen3-235B-A22B-Thinking-2507
Qwen3-235B-A22B-Thinking-2507 is an updated thinking-mode version of Qwen3-235B-A22B, released as a separate reasoning model in the Qwen3-2507 series, which split the hybrid Qwen3 model into dedicated instruct and thinking models.
- Modalities
- text → text
- Context
- 256K context
- Parameters
- MoE: 235B total, 22B active
- License
- Apache-2.0
- At launch
- Open weights
- Native 262,144-token context
- Qwen3-30B-A3B-Thinking-2507 followed on July 31 and Qwen3-4B-Thinking-2507 on August 6, 2025
- Weights under the Apache 2.0 license
Qwen-MT
Qwen-MT (qwen-mt-turbo) is Qwen's translation model on the Qwen API, built on Qwen3 and trained on trillions of multilingual and translation tokens. It uses a lightweight mixture-of-experts architecture for low latency.
- Modalities
- text → text
- At launch
- API
- Translates across 92 major languages and dialects
- Supports terminology intervention, domain prompts, and translation memory
- Available through Alibaba Cloud Model Studio
Qwen3-Coder
Qwen3-Coder is Alibaba's agentic coding model family, led by Qwen3-Coder-480B-A35B-Instruct. Alibaba also open-sourced Qwen Code, a command-line tool for agentic coding in the terminal, alongside it.
- Modalities
- text → text
- Context
- 256K context
- Parameters
- MoE: 480B total, 35B active
- License
- Apache-2.0
- At launch
- API, Open weights
- Pre-trained on 7.5T tokens with a 70% code ratio
- Native 256K context, extendable to 1M with YaRN
- Qwen3-Coder-30B-A3B-Instruct followed on July 31, 2025
- Weights under the Apache 2.0 license
Qwen3-235B-A22B-Instruct-2507
Qwen3-235B-A22B-Instruct-2507 is an updated non-thinking version of Qwen3-235B-A22B with significant improvements and 256K-token long-context understanding. It began the Qwen3-2507 series of separate instruct and thinking models.
- Modalities
- text → text
- Context
- 256K context
- Parameters
- MoE: 235B total, 22B active
- License
- Apache-2.0
- At launch
- Open weights
- Native 262,144-token context; 1M-token support added August 8, 2025
- Qwen3-30B-A3B-Instruct-2507 followed on July 30 and Qwen3-4B-Instruct-2507 on August 6, 2025
- Weights under the Apache 2.0 license
June 2025
4 releasesQwen-TTS
Qwen-TTS is Qwen's text-to-speech model on the Qwen API, trained on millions of hours of speech. This update added support for several Chinese dialects.
- Modalities
- text → audio
- At launch
- API
- Model IDs qwen-tts-latest and qwen-tts-2025-05-22
- Generates 3 Chinese dialects: Pekingese, Shanghainese, and Sichuanese
- Available through the Qwen API
Qwen VLo
Qwen VLo is a preview unified multimodal understanding and generation model from Qwen, which generates high-quality image recreations based on its understanding of the input.
- Modalities
- text, image → image
- At launch
- Consumer app
- Preview version available through Qwen Chat
- Supports instructions in multiple languages, including Chinese and English
- Extends Qwen's vision models from understanding the world to depicting it
Qwen3-Embedding
Qwen3-Embedding is a series of text embedding models built on Qwen3 foundation models, released in 0.6B, 4B, and 8B sizes for retrieval, clustering, and classification.
- Modalities
- text → text
- Context
- 32K context
- Parameters
- 0.6B, 4B, 8B
- License
- Apache-2.0
- At launch
- Open weights
- Released together with the Qwen3-Reranker series
- 32K context length
- Weights on Hugging Face and ModelScope under the Apache 2.0 license
Qwen3-Reranker
Qwen3-Reranker is a series of text reranking models built on Qwen3 foundation models, released alongside Qwen3-Embedding for retrieval pipelines that rerank candidates found by dense embedding search.
- Modalities
- text → text
- Context
- 32K context
- Parameters
- 0.6B, 4B, 8B
- License
- Apache-2.0
- At launch
- Open weights
- Available in 0.6B, 4B, and 8B sizes
- 32K context length
- Weights under the Apache 2.0 license
May 2025
1 releaseWan2.1-VACE
Wan2.1-VACE is an all-in-one model for video creation and editing in the Wan2.1 family, released with inference code, weights, and a technical report.
- Modalities
- text, image, video → video
- Parameters
- 1.3B, 14B
- License
- Apache-2.0
- At launch
- Open weights
- Released in 1.3B and 14B sizes
- Handles multiple video creation and editing tasks in one model
- Released under the Apache 2.0 license
April 2025
1 releaseQwen3
Qwen3 is Alibaba's open-weights model family of two mixture-of-experts models and six dense models from 0.6B to 32B parameters. The models offer hybrid thinking and non-thinking modes with user control over how much reasoning a task receives.
- Modalities
- text → text
- Context
- 32K context
- Parameters
- MoE: 235B total, 22B active (flagship); 0.6B to 32B dense
- License
- Apache-2.0
- At launch
- API, Consumer app, Open weights
- Pre-trained on about 36T tokens covering 119 languages and dialects
- Flagship Qwen3-235B-A22B supports 32,768 tokens natively and 131,072 with YaRN
- Weights under the Apache 2.0 license
March 2025
4 releasesQVQ-Max
QVQ-Max is the first official version of Qwen's visual reasoning model, following the exploratory QVQ-72B-Preview. It understands images and videos and reasons over them to solve problems.
- Modalities
- text, image, video → text
- At launch
- Consumer app
- Accuracy improves as the maximum thinking length increases, per Qwen
- Covers math problems, everyday questions, code, and creative tasks
- Available to try on Qwen Chat
Qwen2.5-Omni
Qwen2.5-Omni is Qwen's end-to-end multimodal model that perceives text, images, audio, and video and responds with text and natural speech in a streaming manner. It uses a Thinker-Talker architecture.
- Modalities
- text, image, audio, video → text, audio
- Parameters
- 7B
- License
- Apache-2.0
- At launch
- Consumer app, Open weights
- Released as Qwen2.5-Omni-7B; a 3B version followed on April 30, 2025
- Available on Qwen Chat
- Weights under the Apache 2.0 license
Qwen2.5-VL-32B
Qwen2.5-VL-32B-Instruct is a 32B vision-language model in the Qwen2.5-VL series, further optimized with reinforcement learning. Its responses align more closely with human preferences.
- Modalities
- text, image, video → text
- Context
- 32K context
- Parameters
- 32B
- License
- Apache-2.0
- At launch
- Open weights
- Stronger mathematical reasoning and fine-grained image understanding
- Released under the Apache 2.0 license
- Weights on Hugging Face and ModelScope
QwQ-32B
QwQ-32B is Qwen's 32B reasoning model trained with scaled reinforcement learning, which Qwen says performs comparably to the much larger DeepSeek-R1. It integrates agent capabilities for reasoning with tools.
- Modalities
- text → text
- Context
- 128K context
- Parameters
- 32B
- License
- Apache-2.0
- At launch
- Consumer app, Open weights
- Full 131,072-token context length
- Accessible via Qwen Chat
- Weights on Hugging Face and ModelScope under the Apache 2.0 license
February 2025
2 releasesQwQ-Max-Preview
QwQ-Max-Preview is a preview of Qwen's QwQ-Max reasoning model, built on Qwen2.5-Max and strong in math, coding, and agent tasks. Qwen said it planned to open-source QwQ-Max and Qwen2.5-Max under Apache 2.0.
- Modalities
- text → text
- At launch
- Consumer app
- Available on Qwen Chat
- Announced alongside plans for a Qwen Chat app
- Qwen also planned smaller open reasoning models such as QwQ-32B
Wan2.1
Wan2.1 is Alibaba's open video generation model family, released with inference code and weights for text-to-video and image-to-video at 1.3B and 14B sizes.
- Modalities
- text, image → video
- Parameters
- 1.3B, 14B
- License
- Apache-2.0
- At launch
- Open weights
- Text-to-video in 1.3B and 14B; image-to-video 14B at 480P and 720P
- First-last-frame-to-video model Wan2.1-FLF2V-14B followed April 17, 2025
- Released under the Apache 2.0 license
January 2025
3 releasesQwen2.5-Max
Qwen2.5-Max is a large-scale mixture-of-experts model pre-trained on more than 20T tokens and post-trained with supervised fine-tuning and RLHF. Qwen released its API through Alibaba Cloud.
- Modalities
- text → text
- At launch
- API, Consumer app
- Mixture-of-experts architecture
- API available through Alibaba Cloud Model Studio
- Available to try on Qwen Chat
Qwen2.5-1M
Qwen2.5-1M is the first set of open Qwen models upgraded to handle 1M-token contexts, released as Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M with a vLLM-based inference framework.
- Modalities
- text → text
- Context
- 1M context
- Parameters
- 7B, 14B
- License
- Apache-2.0
- At launch
- Open weights
- Context length of 1,010,000 tokens with 8,192-token generation
- Inference framework with sparse attention processes 1M-token inputs 3 to 7 times faster
- Weights under the Apache 2.0 license
Qwen2.5-VL
Qwen2.5-VL is Qwen's vision-language model series released in 3B, 7B, and 72B sizes as base and instruct models. The flagship Qwen2.5-VL-72B-Instruct covers document understanding, video understanding, and visual agent tasks.
- Modalities
- text, image, video → text
- Context
- 32K context
- Parameters
- 3B, 7B, 72B
- License
- Apache-2.0 (7B); Qwen License Agreement (72B); Qwen Research License Agreement (3B)
- At launch
- Consumer app, Open weights
- Qwen2.5-VL-72B-Instruct available on Qwen Chat
- Qwen2.5-VL-3B targets edge AI
- Weights on Hugging Face and ModelScope
December 2024
1 releaseQVQ-72B-Preview
QVQ-72B-Preview is an experimental open-weights model for multimodal reasoning, built on Qwen2-VL-72B. It improves math-related visual reasoning compared with Qwen2-VL-72B-Instruct.
- Modalities
- text, image → text
- Parameters
- 72B
- License
- Qwen License Agreement
- At launch
- Open weights
- Experimental research model with known limitations such as language mixing
- Built upon Qwen2-VL-72B
- Weights under the Qwen License Agreement
November 2024
3 releasesQwQ-32B-Preview
QwQ-32B-Preview (Qwen with Questions) is an experimental open-weights reasoning model from the Qwen team, focused on advancing AI reasoning in math, code, and general knowledge.
- Modalities
- text → text
- Context
- 32K context
- Parameters
- 32B
- License
- Apache-2.0
- At launch
- Open weights
- Full 32,768-token context length
- Experimental release with limitations such as language mixing and recursive reasoning loops
- Weights under the Apache 2.0 license
Qwen2.5-Turbo
Qwen2.5-Turbo is a version of Qwen2.5 that supports a 1M-token context, offered through the Alibaba Cloud Model Studio API. It uses sparse attention mechanisms to speed up long-context processing.
- Modalities
- text → text
- Context
- 1M context
- At launch
- API
- Time to first token for 1M-token context cut from 4.9 minutes to 68 seconds
- Compatible with the OpenAI API format
- Demos available on Hugging Face and ModelScope
Qwen2.5-Coder (0.5B to 32B)
The Qwen2.5-Coder series expanded to six sizes with the release of 0.5B, 3B, 14B, and 32B models, led by Qwen2.5-Coder-32B-Instruct. Qwen says the 32B model matches GPT-4o's coding capabilities.
- Modalities
- text → text
- Context
- 128K context
- Parameters
- 0.5B, 1.5B, 3B, 7B, 14B, 32B
- License
- Apache-2.0 (3B uses the Qwen Research License Agreement)
- At launch
- Open weights
- Adds four sizes to the earlier 1.5B and 7B models
- Full 131,072-token context for the larger models
- Most sizes under Apache 2.0
September 2024
3 releasesQwen2.5
Qwen2.5 is Qwen's family of dense decoder-only language models from 0.5B to 72B parameters, pre-trained on up to 18T tokens. It added 3B, 14B, and 32B sizes and launched alongside Qwen2.5-Coder and Qwen2.5-Math.
- Modalities
- text → text
- Context
- 128K context
- Parameters
- 0.5B, 1.5B, 3B, 7B, 14B, 32B, 72B
- License
- Apache-2.0 (3B and 72B use the Qwen Research License and Qwen License)
- At launch
- API, Open weights
- Full 131,072-token context with 8,192-token generation for the larger models
- All open models except 3B and 72B under Apache 2.0
- Qwen2-VL-72B weights were also open-sourced the same day
Qwen2.5-Coder
Qwen2.5-Coder is the next generation of Qwen's open code models, renaming CodeQwen to Qwen-Coder. It continues Qwen2.5 training on 5.5T tokens of code, text-code grounding, and synthetic data.
- Modalities
- text → text
- Context
- 125K context
- Parameters
- 1.5B, 7B
- License
- Apache-2.0
- At launch
- Open weights
- Supports up to 128K tokens of context
- Covers 92 programming languages
- Released in 1.5B and 7B sizes, with 32B announced as coming soon
Qwen2.5-Math
Qwen2.5-Math is Qwen's upgraded math model series with base and instruct models at 1.5B, 7B, and 72B plus the Qwen2.5-Math-RM-72B reward model. It solves English and Chinese math problems with chain-of-thought and tool-integrated reasoning.
- Modalities
- text → text
- Context
- 4K context
- Parameters
- 1.5B, 7B, 72B
- License
- Apache-2.0 (72B uses the Qwen License Agreement)
- At launch
- Open weights
- Supports both chain-of-thought and tool-integrated reasoning
- Pre-trained on Qwen Math Corpus v2 with a 4K context length
- Qwen does not recommend it for non-math tasks
August 2024
3 releasesQwen2-VL
Qwen2-VL is Qwen's vision-language model series based on Qwen2, with improved understanding of images at various resolutions and videos longer than 20 minutes. Qwen open-sourced the 2B and 7B models and released an API for the 72B model.
- Modalities
- text, image, video → text
- Parameters
- 2B, 7B, 72B
- License
- Apache-2.0
- At launch
- API, Open weights
- Understands multilingual text inside images, including most European languages, Japanese, Korean, and Arabic
- 2B and 7B released under Apache 2.0
- Qwen2-VL-72B-Instruct weights followed on September 19, 2024
Qwen2-Audio
Qwen2-Audio is the next version of Qwen-Audio, accepting audio and text input for voice chat and audio analysis. It understands more than 8 languages and dialects.
- Modalities
- text, audio → text
- Parameters
- 7B
- License
- Apache-2.0
- At launch
- Open weights
- Released as Qwen2-Audio-7B and Qwen2-Audio-7B-Instruct
- Supports voice chat and audio analysis modes
- Weights on Hugging Face and ModelScope under the Apache 2.0 license
Qwen2-Math
Qwen2-Math is Qwen's first series of math-specific language models, initialized from Qwen2 1.5B, 7B, and 72B and pre-trained on a mathematics-specific corpus. It mainly supports English at launch.
- Modalities
- text → text
- Parameters
- 1.5B, 7B, 72B
- License
- Apache-2.0 (72B uses the Tongyi Qianwen License Agreement)
- At launch
- Open weights
- Released as base and instruct models
- Bilingual English and Chinese math models were announced as coming
- Smaller sizes under Apache 2.0
June 2024
1 releaseQwen2
Qwen2 is Qwen's second-generation model series of base and instruction-tuned models in five sizes, including the Qwen2-57B-A14B mixture-of-experts model. Base models were pre-trained with 32K context.
- Modalities
- text → text
- Context
- 125K context
- Parameters
- 0.5B, 1.5B, 7B, 57B-A14B, 72B
- License
- Apache-2.0 (72B uses the Tongyi Qianwen License Agreement)
- At launch
- Open weights
- Qwen2-7B-Instruct and Qwen2-72B-Instruct handle up to 128K tokens with YaRN
- Includes Qwen2-0.5B, 1.5B, 7B, 57B-A14B, and 72B
- Smaller sizes under Apache 2.0
May 2024
1 releaseQwen-Max-0428
Qwen-Max-0428 is an instruction-tuned Qwen model for chat services, larger than the open Qwen1.5-110B. It reached the top 10 of the Chatbot Arena leaderboard shortly after release.
- Modalities
- text → text
- At launch
- API
- Available through the DashScope API
- DashScope API became compatible with the OpenAI API format
- Outperforms Qwen1.5-110B-Chat on MT-Bench, per Qwen
April 2024
3 releasesQwen1.5-110B
Qwen1.5-110B is the first 100B-plus model in the Qwen1.5 series, built with the same Transformer decoder architecture as other Qwen1.5 models.
- Modalities
- text → text
- Context
- 32K context
- Parameters
- 110B
- License
- Tongyi Qianwen License Agreement
- At launch
- Open weights
- 32K-token context length
- Multilingual, including English, Chinese, French, Spanish, German, Russian, Korean, and Japanese
- Weights under the Tongyi Qianwen License Agreement
CodeQwen1.5
CodeQwen1.5-7B is a specialized code model built on the Qwen1.5 language model and pre-trained on around 3T tokens of code-related data.
- Modalities
- text → text
- Context
- 64K context
- Parameters
- 7B
- License
- Tongyi Qianwen License Agreement
- At launch
- Open weights
- Supports 92 programming languages
- Processes up to 64K tokens of context
- Weights under the Tongyi Qianwen License Agreement
Qwen1.5-32B
Qwen1.5-32B and Qwen1.5-32B-Chat are mid-size additions to the Qwen1.5 series, aimed at balancing performance, efficiency, and memory footprint at about 30 billion parameters.
- Modalities
- text → text
- Context
- 32K context
- Parameters
- 32B
- License
- Tongyi Qianwen License Agreement
- At launch
- Open weights
- Released as base and chat models
- Uses the same 32K context as other Qwen1.5 models
- Weights under the Tongyi Qianwen License Agreement
March 2024
1 releaseQwen1.5-MoE-A2.7B
Qwen1.5-MoE-A2.7B is Qwen's first mixture-of-experts model, with 2.7B activated parameters, created by repurposing Qwen-1.8B. Qwen reports it matches leading 7B models.
- Modalities
- text → text
- Parameters
- MoE: 2.7B active
- License
- Tongyi Qianwen License Agreement
- At launch
- Open weights
- Contains 2.0B non-embedding parameters, about one-third of Qwen1.5-7B
- Upcycled from the dense Qwen-1.8B model
- Weights under the Tongyi Qianwen License Agreement
February 2024
1 releaseQwen1.5
Qwen1.5 is the next iteration of the Qwen series, open-sourcing base and chat models across multiple sizes with quantized versions. It improved the developer experience with Hugging Face Transformers integration.
- Modalities
- text → text
- Context
- 32K context
- Parameters
- 0.5B, 1.8B, 4B, 7B, 14B, 72B
- License
- Tongyi Qianwen License Agreement
- At launch
- Open weights
- All models support a context length of up to 32,768 tokens
- Released just before the Chinese New Year with GPTQ, AWQ, and GGUF quantized models; code merged into Hugging Face Transformers
- Weights under the Tongyi Qianwen License Agreement
January 2024
1 releaseQwen-VL-Max
Qwen-VL-Max is Qwen's most capable vision-language model at launch, an upgrade over Qwen-VL-Plus with better detailed and text recognition. It supports images up to millions of pixels at arbitrary aspect ratios.
- Modalities
- text, image → text
- At launch
- API, Consumer app
- Accessible through Hugging Face Spaces, the Qwen website, and DashScope APIs
- Upgraded alongside Qwen-VL-Plus
- Proprietary successor to the open Qwen-VL
November 2023
2 releasesQwen-72B and Qwen-1.8B
Qwen-72B is the largest first-generation Qwen model, trained on 3T tokens with 32K context, released with the compact Qwen-1.8B and chat versions of both.
- Modalities
- text → text
- Context
- 32K context
- Parameters
- 1.8B, 72B
- License
- Tongyi Qianwen License Agreement (1.8B uses the Tongyi Qianwen Research License Agreement)
- At launch
- Open weights
- Qwen-72B trained on 3.0T tokens; Qwen-1.8B on 2.2T
- Both support 32K context
- Released on ModelScope and Hugging Face
Qwen-Audio
Qwen-Audio is Qwen's audio-language model that accepts diverse audio and text input, released with the instruction-tuned Qwen-Audio-Chat. Its technical paper was published on November 15, 2023.
- Modalities
- text, audio → text
- License
- Tongyi Qianwen License Agreement
- At launch
- Open weights
- Checkpoints for Qwen-Audio and Qwen-Audio-Chat on ModelScope and Hugging Face
- Commercial use allowed under its license
- Followed by Qwen2-Audio in August 2024
September 2023
1 releaseQwen-14B
Qwen-14B is a first-generation Qwen base model released with the Qwen-14B-Chat assistant model, along with the qwen.cpp runtime and the Qwen-Agent framework.
- Modalities
- text → text
- Context
- 8K context
- Parameters
- 14B
- License
- Tongyi Qianwen License Agreement
- At launch
- Open weights
- Pre-trained on 3.0T tokens
- 8K maximum length
- Released on ModelScope and Hugging Face
August 2023
2 releasesQwen-VL
Qwen-VL is Qwen's first open vision-language model, released with Qwen-VL-Chat. It uses 448 by 448 image resolution for fine-grained text recognition, document question answering, and bounding box annotation.
- Modalities
- text, image → text
- License
- Tongyi Qianwen License Agreement
- At launch
- Open weights
- 448 by 448 resolution, higher than the 224 by 224 used by other open models at the time
- Released on ModelScope and Hugging Face with a paper
- Commercial use allowed under its license
Qwen-7B
Qwen-7B is the first open model from Alibaba's Qwen (Tongyi Qianwen) team, released with the Qwen-7B-Chat assistant model on ModelScope and Hugging Face.
- Modalities
- text → text
- Parameters
- 7B
- License
- Tongyi Qianwen License Agreement
- At launch
- Open weights
- Pre-trained on 2.4T tokens
- Released with a technical memo on training details
- Weights under the Tongyi Qianwen License Agreement
Cite and reuse this data
These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL.
Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".
Citation
The AI Engineering Editors. "Alibaba Qwen models: release history and timeline." The AI Engineering, updated Nov 16, 2026. https://theaiengineering.com/releases/alibaba-qwen
HTML link
<a href="https://theaiengineering.com/releases/alibaba-qwen">Alibaba Qwen models: release history and timeline</a> (The AI Engineering)- Full dataset
- 1,167 releases from 55 labs
- Coverage
- to
- Updated
- License
- CC BY 4.0
- Publisher
- The AI Engineering
Other labs
Google106
OpenAI79Mistral AI59
Meta44
- Z.ai43
Microsoft42Tencent42
- ByteDance Seed40
- DeepSeek38
- Liquid AI34
Cohere31- IBM30
xAI30- NVIDIA29
MiniMax28
Stability AI28- Anthropic26
Ai223StepFun22
Amazon21- Baidu21
- ElevenLabs21
Black Forest Labs18
- Kuaishou16
- Meituan16
Runway16- Moonshot AI15
Midjourney14Salesforce13
- Xiaomi13
Nous Research11- Perplexity10
AI21 Labs8- Apple8
Ideogram8
01.AI7
Hugging Face7
Lightricks7Luma AI7
Reka7- Suno7
- Databricks5
Leonardo.Ai5- Pika5
Recraft5
Inflection AI3MBZUAI IFM3
- Snowflake3
Thinking Machines Lab3
TypeSafe AI2- Cognition1
Genmo1Reflection AI1
Ricursive Intelligence1