Hunyuan A13B Instruct
Summary
Hunyuan A13B Instruct is an open-weight language model from Tencent (Hunyuan), released on 8 Jul 2025. It accepts text and generates text, with a 131K-token context window and up to 118K output tokens per response. It is scheduled for retirement on 15 Nov 2026.
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Tencent (Hunyuan) |
|---|---|
| Release date | 8 Jul 2025 [OpenRouter] |
| Status | Generally available |
| Weights | Open weights [Hugging Face] |
| License | tencent-hunyuan-a13b [Hugging Face] |
| Parameters | 80.4B [Hugging Face] |
| Context window | 131K (131,072 tokens) [OpenRouter] |
| Max output | 118K tokens [OpenRouter] |
| Knowledge cutoff | 31 Mar 2025 [OpenRouter] |
| Input | Text [OpenRouter] |
| Output | Text [OpenRouter] |
| Reasoning mode | Yes [OpenRouter] |
| Tool calling | No [OpenRouter] |
| Structured output | Yes [OpenRouter] |
| Retirement date | 15 Nov 2026 [OpenRouter] |
| Hugging Face | tencent/Hunyuan-A13B-Instruct [Hugging Face] |
Hunyuan A13B Instruct 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 Hunyuan A13B Instruct 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) | 49 GB | 51 GB | 54 GB |
| Q8_0 (8-bit) | 85 GB | 87 GB | 91 GB |
| FP16 / BF16 (16-bit) | 161 GB | 163 GB | 166 GB |
At 4-bit with an 8K conversation, Hunyuan A13B Instruct 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 Hunyuan A13B Instruct?
Hunyuan A13B Instruct has a context window of 131,072 tokens (131K) and can generate up to 117,964 tokens in a single response, according to OpenRouter.
Is Hunyuan A13B Instruct open source?
Hunyuan A13B Instruct is an open-weight model: its weights are published on Hugging Face as tencent/Hunyuan-A13B-Instruct under the tencent-hunyuan-a13b license. Check the license terms before commercial use.
When was Hunyuan A13B Instruct released?
Tencent (Hunyuan) released Hunyuan A13B Instruct on 8 Jul 2025, according to OpenRouter.
How much VRAM does Hunyuan A13B Instruct need?
About 51 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 87 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.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Kimi K2 Instruct | Moonshot AI | 11 Jul 2025 | 131K | $0.57 | $2.30 | Open |
| Kimi-K2-Instruct | Moonshot AI | 11 Jul 2025 | 131K | $0.57 | $2.30 | Open |
| Uncensored | Cognitivecomputations | 9 Jul 2025 | 128K | $0.20 | $0.90 | Open |
| UI-TARS 7B | Bytedance | 22 Jul 2025 | 128K | $0.10 | $0.20 | Open |
| ERNIE 4.5 300B A47B | Baidu | 30 Jun 2025 | 123K | – | – | Open |
| ERNIE 4.5 VL 424B A47B | Baidu | 30 Jun 2025 | 123K | – | – | Open |
Change history
- No longer listed on openrouter
- Retirement date changed from none to 15 Nov 2026