Alibaba (Qwen)

Qwen3 8B

DeprecatedOpen weights131K contextReasoning

Summary

Qwen3 8B 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 8K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.06 per million input tokens and $0.06 per million output tokens (SiliconFlow), across 2 providers we track. It is scheduled for retirement on 9 Oct 2026.

Qwen instruction model for multilingual chat, reasoning, and tool use

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]
Parameters8.2B [Hugging Face]
Context window131K (131,072 tokens) [models.dev]
Max output8K tokens [models.dev]
Knowledge cutoffApr 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Retirement date9 Oct 2026 [OpenRouter]
Hugging FaceQwen/Qwen3-8B [Hugging Face]

Qwen3 8B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
SiliconFlow
Qwen/Qwen3-8B
$0.06$0.06–131Kmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
Qwen/Qwen3-8B
$0.07$0.18–41Kmodels.dev, 18 Nov 2026

Running Qwen3 8B 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)5.0 GB7.0 GB11 GB
Q8_0 (8-bit)8.7 GB11 GB14 GB
FP16 / BF16 (16-bit)16 GB18 GB22 GB

At 4-bit with an 8K conversation, Qwen3 8B needs about 7.0 GB, so it fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 GB. Check your own hardware, or see Running local LLMs on an 8 GB GPU on our sister site AIPCs.

Frequently asked questions

What is the context window of Qwen3 8B?

Qwen3 8B has a context window of 131,072 tokens (131K) and can generate up to 8,192 tokens in a single response, according to models.dev.

How much does the Qwen3 8B API cost?

Qwen3 8B is listed from $0.06 per million input tokens and $0.06 per million output tokens (SiliconFlow). Prices last verified 18 Nov 2026.

Is Qwen3 8B open source?

Qwen3 8B is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-8B under the apache-2.0 license. Check the license terms before commercial use.

When was Qwen3 8B released?

Alibaba (Qwen) released Qwen3 8B on Apr 2025, according to models.dev.

Which providers offer Qwen3 8B?

We track Qwen3 8B on 2 providers: SiliconFlow, Hugging Face Inference Providers.

How much VRAM does Qwen3 8B need?

About 7.0 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 11 GB at 8-bit. The 4-bit model fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 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
Gemma 3 12B ITGoogle DeepMind12 Mar 2025131K$0.05$0.10Open
Gemma 3 4B ITGoogle DeepMind12 Mar 2025131K$0.05$0.10Open
DeepSeek R1 0528 Qwen3 8BDeepSeek29 May 2025128K$0.06$0.09Open
Command R7B ArabicCohere27 Feb 2025128K$0.04$0.15Open
gpt-oss-20bOpenAI5 Aug 2025131K$0.02$0.09Open
Baichuan M2 32BBaichuan13 Aug 2025131K$0.07$0.07Open

Change history

  • Now listed on Hugging Face Inference Providers
  • Now listed on SiliconFlow
  • No longer listed on alibaba
  • Status changed from active to deprecated
  • No longer listed on openrouter

Sources