Qwen3 8B
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
| 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 | 8.2B [Hugging Face] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 8K 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] |
| Retirement date | 9 Oct 2026 [OpenRouter] |
| Hugging Face | Qwen/Qwen3-8B [Hugging Face] |
Qwen3 8B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| SiliconFlow Qwen/Qwen3-8B | $0.06 | $0.06 | – | 131K | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers Qwen/Qwen3-8B | $0.07 | $0.18 | – | 41K | models.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.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 5.0 GB | 7.0 GB | 11 GB |
| Q8_0 (8-bit) | 8.7 GB | 11 GB | 14 GB |
| FP16 / BF16 (16-bit) | 16 GB | 18 GB | 22 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.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Gemma 3 12B IT | Google DeepMind | 12 Mar 2025 | 131K | $0.05 | $0.10 | Open |
| Gemma 3 4B IT | Google DeepMind | 12 Mar 2025 | 131K | $0.05 | $0.10 | Open |
| DeepSeek R1 0528 Qwen3 8B | DeepSeek | 29 May 2025 | 128K | $0.06 | $0.09 | Open |
| Command R7B Arabic | Cohere | 27 Feb 2025 | 128K | $0.04 | $0.15 | Open |
| gpt-oss-20b | OpenAI | 5 Aug 2025 | 131K | $0.02 | $0.09 | Open |
| Baichuan M2 32B | Baichuan | 13 Aug 2025 | 131K | $0.07 | $0.07 | Open |
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
- https://openrouter.ai/qwen/qwen3-8b
- https://github.com/sst/models.dev/blob/dev/providers/alibaba/models/qwen3-8b.toml
- https://huggingface.co/Qwen/Qwen3-8B
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/Qwen/Qwen3-8B.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-8B.toml