Alibaba (Qwen)

Qwen3-Next 80B-A3B (Thinking)

DeprecatedOpen weights131K contextReasoning

Summary

Qwen3-Next 80B-A3B (Thinking) is an open-weight language model from Alibaba (Qwen), released on Sept 2025. It accepts text and generates text, with a 131K-token context window and up to 33K output tokens per response. It is scheduled for retirement on 9 Oct 2026.

Efficient Qwen thinking model for local reasoning, math, and coding agents

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

Specifications

DeveloperAlibaba (Qwen)
Release dateSept 2025 [models.dev]
StatusDeprecated [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters81.3B [Hugging Face]
Context window131K (131,072 tokens) [models.dev]
Max output33K 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-Next-80B-A3B-Thinking [Hugging Face]

Qwen3-Next 80B-A3B (Thinking) API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Running Qwen3-Next 80B-A3B (Thinking) 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)49 GB51 GB53 GB
Q8_0 (8-bit)86 GB88 GB90 GB
FP16 / BF16 (16-bit)163 GB164 GB167 GB

At 4-bit with an 8K conversation, Qwen3-Next 80B-A3B (Thinking) needs about 51 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of Qwen3-Next 80B-A3B (Thinking)?

Qwen3-Next 80B-A3B (Thinking) 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.

Is Qwen3-Next 80B-A3B (Thinking) open source?

Qwen3-Next 80B-A3B (Thinking) is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-Next-80B-A3B-Thinking under the apache-2.0 license. Check the license terms before commercial use.

When was Qwen3-Next 80B-A3B (Thinking) released?

Alibaba (Qwen) released Qwen3-Next 80B-A3B (Thinking) on Sept 2025, according to models.dev.

How much VRAM does Qwen3-Next 80B-A3B (Thinking) need?

About 51 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 88 GB at 8-bit. That is more than any single consumer graphics card holds. 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
Hermes-4-405BNousresearch26 Aug 2025131K$1$3Open
Nvidia Nemotron Nano 9B V2NVIDIA18 Aug 2025131K$0.06$0.23Open
Baichuan M2 32BBaichuan13 Aug 2025131K$0.07$0.07Open
Magistral Small 1.2Mistral AI18 Sept 2025128K$0.50$1.50Open
Cydonia 24B V4.1Thedrummer27 Sept 2025131K$0.30$0.50Open
Cydonia 24B V4.1Thedrummer27 Sept 2025131K––Open

Change history

  • No longer listed on vercel
  • No longer listed on openrouter
  • No longer listed on huggingface
  • Status changed from active to deprecated
  • No longer listed on alibaba
  • No longer listed on novita-ai

Sources