Qwen3-30B-A3B-Instruct-2507
Summary
Qwen3-30B-A3B-Instruct-2507 is an open-weight language model from Alibaba (Qwen), released on 28 Jul 2025. It accepts text and generates text, with a 262K-token context window and up to 8K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.09 per million input tokens and $0.30 per million output tokens (SiliconFlow), across 3 providers we track.
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
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | 28 Jul 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 30.5B [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 8K tokens [models.dev] |
| Knowledge cutoff | Dec 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | Qwen/Qwen3-30B-A3B-Instruct-2507 [Hugging Face] |
Qwen3-30B-A3B-Instruct-2507 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| SiliconFlow Qwen/Qwen3-30B-A3B-Instruct-2507 | $0.09 | $0.30 | – | 262K | models.dev, 18 Nov 2026 |
| Nebius AI Studio Qwen/Qwen3-30B-A3B-Instruct-2507 | $0.10 | $0.30 | $0.10 | 262K | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen3-30b-a3b-instruct-2507 | $0.10 | $0.30 | $0.10 | 262K | OpenRouter, 18 Nov 2026 |
Running Qwen3-30B-A3B-Instruct-2507 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) | 19 GB | 20 GB | 23 GB |
| Q8_0 (8-bit) | 32 GB | 34 GB | 36 GB |
| FP16 / BF16 (16-bit) | 61 GB | 63 GB | 65 GB |
At 4-bit with an 8K conversation, Qwen3-30B-A3B-Instruct-2507 needs about 20 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 Qwen3-30B-A3B-Instruct-2507?
Qwen3-30B-A3B-Instruct-2507 has a context window of 262,144 tokens (262K) and can generate up to 8,192 tokens in a single response, according to models.dev.
How much does the Qwen3-30B-A3B-Instruct-2507 API cost?
Qwen3-30B-A3B-Instruct-2507 is listed from $0.09 per million input tokens and $0.30 per million output tokens (SiliconFlow). Prices last verified 18 Nov 2026.
Is Qwen3-30B-A3B-Instruct-2507 open source?
Qwen3-30B-A3B-Instruct-2507 is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-30B-A3B-Instruct-2507 under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen3-30B-A3B-Instruct-2507 released?
Alibaba (Qwen) released Qwen3-30B-A3B-Instruct-2507 on 28 Jul 2025, according to models.dev.
Which providers offer Qwen3-30B-A3B-Instruct-2507?
We track Qwen3-30B-A3B-Instruct-2507 on 3 providers: SiliconFlow, Nebius AI Studio, OpenRouter.
How much VRAM does Qwen3-30B-A3B-Instruct-2507 need?
About 20 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 34 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 |
|---|---|---|---|---|---|---|
| Mistral Small 3.2 24B | Mistral AI | 20 Jun 2025 | 256K | $0.10 | $0.30 | Open |
| Ministral 14B | Mistral AI | 2 Dec 2025 | 262K | $0.20 | $0.20 | Open |
| UI-TARS 7B | Bytedance | 22 Jul 2025 | 128K | $0.10 | $0.20 | Open |
| ERNIE 4.5 21B A3B | Baidu | 30 Jun 2025 | 120K | $0.07 | $0.28 | Open |
| Llama Guard 4 12B | Meta | 29 Apr 2025 | 164K | $0.18 | $0.18 | Open |
| Step 3.5 Flash | StepFun | 29 Jan 2026 | 262K | $0.10 | $0.30 | Open |
Change history
- OpenRouter price changed: input $0.10 → $0.10, output $0.30 → $0.30 per 1M tokens
- OpenRouter price changed: input $0.09 → $0.10, output $0.30 → $0.30 per 1M tokens
- Release date changed from 29 Jul 2025 to 28 Jul 2025
- Max output changed from 32K to 8K
- Knowledge cutoff changed from 30 Jun 2025 to Dec 2025
- Now listed on Nebius AI Studio
- Now listed on SiliconFlow
- Name changed from Qwen3 30B A3B Instruct 2507 to Qwen3-30B-A3B-Instruct-2507
- OpenRouter price changed: input $0.10 → $0.09, output $0.30 → $0.30 per 1M tokens
- OpenRouter price changed: input $0.05 → $0.10, output $0.19 → $0.30 per 1M tokens
- OpenRouter price changed: input $0.10 → $0.05, output $0.30 → $0.19 per 1M tokens
- OpenRouter price changed: input $0.05 → $0.10, output $0.19 → $0.30 per 1M tokens
Sources
- https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507
- https://github.com/sst/models.dev/blob/dev/providers/nebius/models/Qwen/Qwen3-30B-A3B-Instruct-2507.toml
- https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/Qwen/Qwen3-30B-A3B-Instruct-2507.toml