Alibaba (Qwen)

Qwen3 VL 30B A3B Instruct

Generally availableOpen weights131K context

Summary

Qwen3 VL 30B A3B Instruct is an open-weight language model from Alibaba (Qwen), released on 4 Oct 2025. It accepts text and images and generates text, with a 131K-token context window and up to 33K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.15 per million input tokens and $0.60 per million output tokens (DeepInfra), across 5 providers we track.

Qwen vision-language model for visual reasoning, documents, and agent tasks

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperAlibaba (Qwen)
Release date4 Oct 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters31.1B [Hugging Face]
Context window131K (131,072 tokens) [models.dev]
Max output33K tokens [models.dev]
Knowledge cutoff31 Mar 2025 [OpenRouter]
InputText and images [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging FaceQwen/Qwen3-VL-30B-A3B-Instruct [Hugging Face]

Qwen3 VL 30B A3B Instruct API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
DeepInfra
Qwen/Qwen3-VL-30B-A3B-Instruct
$0.15$0.60–262Kmodels.dev, 18 Nov 2026
OpenRouter
qwen/qwen3-vl-30b-a3b-instruct
$0.15$0.60–262KOpenRouter, 18 Nov 2026
Hugging Face Inference Providers
Qwen/Qwen3-VL-30B-A3B-Instruct
$0.20$0.70–131Kmodels.dev, 18 Nov 2026
Novita AI
qwen/qwen3-vl-30b-a3b-instruct
$0.20$0.70–131Kmodels.dev, 18 Nov 2026
SiliconFlow
Qwen/Qwen3-VL-30B-A3B-Instruct
$0.29$1–262Kmodels.dev, 18 Nov 2026

Running Qwen3 VL 30B A3B Instruct locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)19 GB20 GB23 GB
Q8_0 (8-bit)33 GB35 GB37 GB
FP16 / BF16 (16-bit)62 GB64 GB66 GB

At 4-bit with an 8K conversation, Qwen3 VL 30B A3B Instruct needs about 20 GB, so it fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.

Frequently asked questions

What is the context window of Qwen3 VL 30B A3B Instruct?

Qwen3 VL 30B A3B Instruct has a context window of 131,072 tokens (131K) and can generate up to 32,768 tokens in a single response, according to models.dev.

How much does the Qwen3 VL 30B A3B Instruct API cost?

Qwen3 VL 30B A3B Instruct is listed from $0.15 per million input tokens and $0.60 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.

Is Qwen3 VL 30B A3B Instruct open source?

Qwen3 VL 30B A3B Instruct is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-VL-30B-A3B-Instruct under the apache-2.0 license. Check the license terms before commercial use.

When was Qwen3 VL 30B A3B Instruct released?

Alibaba (Qwen) released Qwen3 VL 30B A3B Instruct on 4 Oct 2025, according to models.dev.

Which providers offer Qwen3 VL 30B A3B Instruct?

We track Qwen3 VL 30B A3B Instruct on 5 providers: DeepInfra, OpenRouter, Hugging Face Inference Providers, Novita AI, SiliconFlow.

How much VRAM does Qwen3 VL 30B A3B Instruct need?

About 20 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 35 GB at 8-bit. The 4-bit model fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Cydonia 24B V4.1Thedrummer27 Sept 2025131K$0.30$0.50Open
GPT OSS Safeguard 120BOpenAI29 Oct 2025128K$0.15$0.60Open
Nvidia Nemotron Nano 12B V2 VLNVIDIA28 Oct 2025131K$0.20$0.60Open
Gemma Sea Lion V4 27B ItAisingapore23 Sept 2025128K$0.35$0.56Open
DeepSeek V3.2 ExpDeepSeek29 Sept 2025164K$0.27$0.41Open
GLM-4.5-AirZhipu AI (Z.ai)28 Jul 2025131K$0.13$0.85Open

Change history

  • Input modalities changed from text, image, video to text, image
  • Context window changed from 262K to 131K
  • Max output changed from 262K to 33K
  • Name changed from Qwen/Qwen3-VL-30B-A3B-Instruct to Qwen3 VL 30B A3B Instruct
  • Input modalities changed from text, image to text, image, video
  • Context window changed from 131K to 262K
  • Name changed from Qwen3 VL 30B A3B Instruct to Qwen/Qwen3-VL-30B-A3B-Instruct
  • Max output changed from 33K to 262K
  • Input modalities changed from text, image, video to text, image
  • Input modalities changed from text, image to text, image, video
  • Context window changed from 262K to 131K
  • Max output changed from 16K to 33K
  • Input modalities changed from text, image, video to text, image
  • Context window changed from 131K to 262K
  • Max output changed from 33K to 16K
  • Context window changed from 262K to 131K
  • Input modalities changed from text, image to text, image, video
  • Name changed from Qwen/Qwen3-VL-30B-A3B-Instruct to Qwen3 VL 30B A3B Instruct
  • Context window changed from 262K to 262K
  • Max output changed from 262K to 33K
  • Name changed from Qwen3 VL 30B A3B Instruct to Qwen/Qwen3-VL-30B-A3B-Instruct
  • Context window changed from 262K to 262K
  • Max output changed from 16K to 262K
  • Max output changed from 33K to 16K
  • Context window changed from 131K to 262K

Sources