Alibaba (Qwen)

Qwen3 32B

DeprecatedOpen weights131K contextReasoning

Summary

Qwen3 32B is an open-weight language model from Alibaba (Qwen), released on Apr 2025. It accepts text and generates text, with a 131K-token context window and up to 16K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.08 per million input tokens and $0.28 per million output tokens (DeepInfra), across 6 providers we track. Alibaba (Qwen) has deprecated this model.

Dense open Qwen model for self-hosted chat, reasoning, and coding

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

Specifications

DeveloperAlibaba (Qwen)
Release dateApr 2025 [models.dev]
StatusDeprecated [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters32.8B [Hugging Face]
Context window131K (131,072 tokens) [models.dev]
Max output16K tokens [models.dev]
Knowledge cutoffApr 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Hugging FaceQwen/Qwen3-32B [Hugging Face]

Qwen3 32B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
DeepInfra
Qwen/Qwen3-32B
$0.08$0.28–41Kmodels.dev, 18 Nov 2026
OpenRouter
qwen/qwen3-32b
$0.08$0.28–41KOpenRouter, 18 Nov 2026
SiliconFlow
Qwen/Qwen3-32B
$0.14$0.57–131Kmodels.dev, 18 Nov 2026
Amazon Bedrock
qwen.qwen3-32b-v1:0
$0.15$0.60–33Kmodels.dev, 18 Nov 2026
Vercel AI Gateway
alibaba/qwen-3-32b
$0.15$0.60–128Kmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
Qwen/Qwen3-32B
$0.29$0.59–131Kmodels.dev, 18 Nov 2026

Running Qwen3 32B 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)20 GB23 GB29 GB
Q8_0 (8-bit)35 GB38 GB44 GB
FP16 / BF16 (16-bit)66 GB68 GB75 GB

At 4-bit with an 8K conversation, Qwen3 32B needs about 23 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 32B?

Qwen3 32B has a context window of 131,072 tokens (131K) and can generate up to 16,384 tokens in a single response, according to models.dev.

How much does the Qwen3 32B API cost?

Qwen3 32B is listed from $0.08 per million input tokens and $0.28 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.

Is Qwen3 32B open source?

Qwen3 32B is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-32B under the apache-2.0 license. Check the license terms before commercial use.

When was Qwen3 32B released?

Alibaba (Qwen) released Qwen3 32B on Apr 2025, according to models.dev.

Which providers offer Qwen3 32B?

We track Qwen3 32B on 6 providers: DeepInfra, OpenRouter, SiliconFlow, Amazon Bedrock, Vercel AI Gateway, Hugging Face Inference Providers.

How much VRAM does Qwen3 32B need?

About 23 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 38 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
Llama-4-Scout-17B-16E-Instruct-FP8Meta5 Apr 2025128K$0.10$0.30Open
Mistral Small 3.1 24BMistral AI17 Mar 2025128K$0.10$0.30Open
Llama Guard 4 12BMeta29 Apr 2025164K$0.18$0.18Open
Gemma 3 27B ITGoogle DeepMind12 Mar 2025131K$0.08$0.16Open
ERNIE 4.5 21B A3BBaidu30 Jun 2025120K$0.07$0.28Open
Phi-4-miniMicrosoft11 Dec 2024128K$0.07$0.30Open

Change history

  • Status changed from active to deprecated
  • No longer listed on alibaba
  • Vercel AI Gateway price changed: input $0.16 → $0.15, output $0.64 → $0.60 per 1M tokens

Sources