# QwQ-32B-Preview

QwQ-32B-Preview is an AI model released by Qwen on Nov 28 2024. It has 32B parameters, a 32k context window and open weight. Tracked results include 50% on LiveCodeBench.

## Facts

| Field | Value |
| --- | --- |
| Model | QwQ-32B-Preview |
| Developer | Qwen |
| Release date | Thursday, Nov 28 2024 |
| Licensing | Open Weight |
| Parameters | 32B |
| Context window | 32k |

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| LiveCodeBench | 50% | Lab | Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. |

## About QwQ-32B-Preview

QwQ-32B-Preview was released in November 2024 as Qwen's experimental reasoning model, focused especially on mathematics and programming. The release explored giving a model more room to examine assumptions, try alternatives and revise its approach before producing an answer. It was an early research checkpoint rather than the later production QwQ-32B model released in 2025.

The Qwen team explicitly documented limitations, including unexpected language switching, circular reasoning and answers that could become long without reaching a conclusion. Those caveats are part of the model's historical significance: longer reasoning could improve technical problem solving while introducing different failure modes. The preview offered a downloadable system for studying that tradeoff, separate from the general Qwen2.5 chat models.

## Questions and answers

### When was QwQ-32B-Preview released?

QwQ-32B-Preview was released by Qwen on Thursday, Nov 28 2024.

### Who made QwQ-32B-Preview?

QwQ-32B-Preview was built by Qwen. Alibaba's AI lab, building the Qwen family. The most prolific publisher of open-weight models of any major lab, alongside a closed Max and Plus tier sold through Alibaba Cloud.

### What benchmark scores did QwQ-32B-Preview get?

QwQ-32B-Preview reports 1 tracked benchmark score — LiveCodeBench: 50%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### What is the context window of QwQ-32B-Preview?

QwQ-32B-Preview has a context window of 32k. Providers may specify separate input and output token limits.

### How many parameters does QwQ-32B-Preview have?

QwQ-32B-Preview is reported at 32B parameters.

### Is QwQ-32B-Preview open source?

Partly. QwQ-32B-Preview is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.

### What came before and after QwQ-32B-Preview?

Qwen's previous tracked release was Qwen2.5-Coder on Nov 12 2024, 16 days earlier. It was followed by Qwen2.5-Max on Jan 28 2025.


---

Canonical page: https://aireleasetracker.com/model/qwen/qwq-32b-preview
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.