Language modelActive

Qwen 3 VL 8B Thinking

Alibaba

Released: October 11, 2025
Data date: September 8, 2026

Speed: 113.1 tokens/s
Output throughput
Price: $0.18 · $2.1
Input · Output / 1M tokens
Input: Text, Image, Video
Output: Text

Qwen 3 VL 8B Thinking brings the Qwen3-VL thinking mode to a much smaller dense checkpoint. It accepts text, images, and video and can connect visual evidence across multi-step answers. The model card lists roughly 8.2 billion parameters and 262,144 context tokens.

Qwen 3 VL 30B A3B Thinking is the larger variant with the same multimodal focus, but an MoE architecture instead of a dense model.

Specifications and access

Specification	Value and source
Weights	Open weightsSource
Access	API, LocalSource
Parameters	8.2BSource
Context window	262,144 tokensSource
Weights repository	Qwen/Qwen3-VL-8B-ThinkingSource
License	Apache-2.0Source
Architecture	vision encoder + MLP vision-language merger + Qwen3 language model; dense or MoESource
Input	Text, Image, VideoSource
Output	TextSource
Reasoning mode	thinkingSource
Tool calling	YesSource
Structured output	YesSource
Native context window	131,072 tokensSource
Maximum context window	262,144 tokensSource
Parameters	8.2 BSource
Languages	39 languages testedSource
Repository created	2025-10-11 (Repository creation date is a precise publication proxy, but may differ from the public announcement date or an individual checkpoint's first availability.)Source

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

MMMU (Show measurement, test conditions, and source)

Source value: 74.1
Score: 74.1
Metric: percent
Unit: %
Category: visual
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3-VL Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Exact model column; report evaluates thinking/instruct variants separately

Source Qwen3-VL Technical Report

MMMU-Pro (Show measurement, test conditions, and source)

Source value: 60.4
Score: 60.4
Metric: percent
Unit: %
Category: visual
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3-VL Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Exact model column; report evaluates thinking/instruct variants separately

Source Qwen3-VL Technical Report

MathVision (Show measurement, test conditions, and source)

Source value: 62.7
Score: 62.7
Metric: percent
Unit: %
Category: visual
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3-VL Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Exact model column; report evaluates thinking/instruct variants separately

Source Qwen3-VL Technical Report

DocVQA test (Show measurement, test conditions, and source)

Source value: 95.3
Score: 95.3
Metric: percent
Unit: %
Category: document
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3-VL Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Exact model column; report evaluates thinking/instruct variants separately

Source Qwen3-VL Technical Report

VideoMME w/o subtitles (Show measurement, test conditions, and source)

Source value: 71.8
Score: 71.8
Metric: percent
Unit: %
Category: video
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3-VL Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Exact model column; report evaluates thinking/instruct variants separately

Source Qwen3-VL Technical Report

OCRBench (Show measurement, test conditions, and source)

Source value: 819
Score: 819
Metric: points
Unit: points
Category: document
Direction: Higher is better
Source type: vendor-reported
Evaluator: Qwen3-VL Technical Report
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Exact model column; report evaluates thinking/instruct variants separately

Source Qwen3-VL Technical Report

Output speed (Show measurement, test conditions, and source)

Source value: 113.090825347068
Score: 113.090825347068
Metric: tokens/s
Unit: tokens/s
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. Reasoning; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Latency reasoning time (Show measurement, test conditions, and source)

Source value: 17.684900555479516
Score: 17.684900555479516
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. Reasoning; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Latency input time (Show measurement, test conditions, and source)

Source value: 2.288705749
Score: 2.288705749
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. Reasoning; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Answer generation time (end-to-end timing breakdown) (Show measurement, test conditions, and source)

Source value: 4.421225138869879
Score: 4.421225138869879
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. Reasoning; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

End-to-end reasoning time component (Show measurement, test conditions, and source)

Source value: 17.684900555479516
Score: 17.684900555479516
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. Reasoning; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

End-to-end input time component (Show measurement, test conditions, and source)

Source value: 2.288705749
Score: 2.288705749
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. Reasoning; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Sources and data date

Type	Evidence and data date
Speed	Alibaba, Reasoning. Output speed after the first streaming chunk, not total response time. Classified as deprecated by Artificial Analysis. Artificial Analysis maintains only the default 10K-input workload there. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · Qwen3-VL-8B-Thinking model card · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · Qwen3-VL-8B-Thinking model card · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	active-parameters-billions Original wording Dense checkpoint; no separate activated-parameter count is applicable/published.
Additional source	Qwen3-VL Technical Report (retrieved September 8, 2026) · Qwen3-VL Technical Report · Editorial description reviewed October 2, 2026
Additional source	Model metadata (retrieved September 8, 2026)
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0

Qwen 3 VL 8B Thinking

Specifications and access

Measurements without matching peer values

Our tests

Pelican on a bicycle

Popularity

Published prices

Sources and data date