QVQ-72B-Preview

Name: QVQ-72B-Preview
Author: Alibaba

AlibabaOpen WeightsPending Human Review

QVQ-72B-Preview is an open-weight visual reasoning model built from Qwen2-VL-72B. It combines image understanding with extended reasoning to tackle mathematical diagrams, science questions, and other visually grounded problems. The release is an experimental preview rather than a general production multimodal service. Public weights and demonstration code support research under the Qwen License Agreement. Its long reasoning behavior and visual question-solving focus distinguish it from the standard Qwen2-VL checkpoint.

2024-12-24

72B

Decoder-only Transformer with vision encoder

Qwen License Agreement

Compare with other models

Specifications

Parameters: 72B
Architecture: Decoder-only Transformer with vision encoder
License: Qwen License Agreement
Context Window: 32,768 tokens
Type: multimodal
Modalities: textimage

Benchmark Scores

Advanced Specifications

Model Family: Qwen
Finetuned From: Qwen2-VL-72B
API Access: Not Available
Chat Interface: Not Available

Capabilities & Limitations

Capabilities: visual reasoningmathematicsscientific reasoning
Known Limitations: Experimental preview with possible repetition and overly long reasoning.Custom Qwen license terms apply; production reliability is not established.
Notable Use Cases: diagram problem solvingvisual reasoning researchmultimodal tutoring prototypes

Resources

Related Models

IndustryLLM

Alibaba

IndustryLLM is Alibaba’s open-weight language model for industrial procurement and engineering-standard reasoning. It adapts Qwen3.5-35B-A3B-Base through continued pre-training on industrial documents and transactions followed by task-focused supervised fine-tuning. The 35.95B-parameter hybrid mixture-of-experts network activates approximately 3B per token. Training targets informal buyer language, ambiguous product codes, contradictory specifications, and evidence-based constraint evaluation. Apache-licensed BF16 weights are published. Its 262K architectural context is distinct from 12,288-token packed fine-tuning sequences; this record uses the supported training length conservatively. The September 25 paper predates later discovery-index coverage.

Typetext

Parameters35.95B total, approximately 3B active

2026-09-25

Open Weights

Details Compare

Qwen-Audio-3.1-Realtime

Alibaba

Qwen-Audio-3.1-Realtime is a proprietary language-capable speech conversation model for fluid real-time dialogue. It combines speech reasoning with duplex interaction, allowing conversational responses rather than only transcription or speech synthesis. The 3.1 Plus update supports a 262,144-token context, function calling, web search, voice cloning, and additional system voices, while retaining the 3.0 Plus integration protocol. Hosted streaming APIs provide access; no downloadable weights or checkpoint parameter count is verified.

Qwen3.8-Omni-Flash

Alibaba

Qwen3.8-Omni-Flash is a native omnimodal agent model built on the Qwen3.8-Flash-Next architecture. It accepts text, images, audio, and video in a million-token context, extending coding, GUI operation, and knowledge work to audio-visual productivity. Standard APIs return text, while the subsequently available Realtime variant supports text and speech output, multichannel audio, video aggregation, and remote MCP tools. Hosted access and companion plugins support video editing, multimedia summarization, and real-time conversations; its weights are not publicly released.