Qwen3 32B
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
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | Apr 2025 [models.dev] |
| Status | Deprecated [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 32.8B [Hugging Face] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 16K tokens [models.dev] |
| Knowledge cutoff | Apr 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Hugging Face | Qwen/Qwen3-32B [Hugging Face] |
Qwen3 32B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepInfra Qwen/Qwen3-32B | $0.08 | $0.28 | – | 41K | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen3-32b | $0.08 | $0.28 | – | 41K | OpenRouter, 18 Nov 2026 |
| SiliconFlow Qwen/Qwen3-32B | $0.14 | $0.57 | – | 131K | models.dev, 18 Nov 2026 |
| Amazon Bedrock qwen.qwen3-32b-v1:0 | $0.15 | $0.60 | – | 33K | models.dev, 18 Nov 2026 |
| Vercel AI Gateway alibaba/qwen-3-32b | $0.15 | $0.60 | – | 128K | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers Qwen/Qwen3-32B | $0.29 | $0.59 | – | 131K | models.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.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 20 GB | 23 GB | 29 GB |
| Q8_0 (8-bit) | 35 GB | 38 GB | 44 GB |
| FP16 / BF16 (16-bit) | 66 GB | 68 GB | 75 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.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Llama-4-Scout-17B-16E-Instruct-FP8 | Meta | 5 Apr 2025 | 128K | $0.10 | $0.30 | Open |
| Mistral Small 3.1 24B | Mistral AI | 17 Mar 2025 | 128K | $0.10 | $0.30 | Open |
| Llama Guard 4 12B | Meta | 29 Apr 2025 | 164K | $0.18 | $0.18 | Open |
| Gemma 3 27B IT | Google DeepMind | 12 Mar 2025 | 131K | $0.08 | $0.16 | Open |
| ERNIE 4.5 21B A3B | Baidu | 30 Jun 2025 | 120K | $0.07 | $0.28 | Open |
| Phi-4-mini | Microsoft | 11 Dec 2024 | 128K | $0.07 | $0.30 | Open |
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
- https://openrouter.ai/qwen/qwen3-32b
- https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3-32b.toml
- https://huggingface.co/Qwen/Qwen3-32B
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3-32B.toml
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/Qwen/Qwen3-32B.toml
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/qwen.qwen3-32b-v1:0.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/alibaba/qwen-3-32b.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-32B.toml