Hy-MT2-1.8B
Summary
Hy-MT2-1.8B is an open-weight language model from Tencent (Hunyuan), released on 20 Aug 2026. It accepts text and generates text, with a 8K-token context window and up to 4K output tokens per response.
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Tencent (Hunyuan) |
|---|---|
| Release date | 20 Aug 2026 [OpenRouter] |
| Status | Generally available |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 2B [Hugging Face] |
| Context window | 8K (8,192 tokens) [OpenRouter] |
| Max output | 4K tokens [OpenRouter] |
| Input | Text [OpenRouter] |
| Output | Text [OpenRouter] |
| Reasoning mode | No [OpenRouter] |
| Tool calling | No [OpenRouter] |
| Structured output | No [OpenRouter] |
| Hugging Face | tencent/Hy-MT2-1.8B [Hugging Face] |
Hy-MT2-1.8B 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 Hy-MT2-1.8B 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) | 1.2 GB | 2.6 GB | 2.6 GB |
| Q8_0 (8-bit) | 2.2 GB | 3.5 GB | 3.5 GB |
| FP16 / BF16 (16-bit) | 4.1 GB | 5.4 GB | 5.4 GB |
At 4-bit with an 8K conversation, Hy-MT2-1.8B needs about 2.6 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 Hy-MT2-1.8B?
Hy-MT2-1.8B has a context window of 8,192 tokens (8K) and can generate up to 4,096 tokens in a single response, according to OpenRouter.
Is Hy-MT2-1.8B open source?
Hy-MT2-1.8B is an open-weight model: its weights are published on Hugging Face as tencent/Hy-MT2-1.8B under the apache-2.0 license. Check the license terms before commercial use.
When was Hy-MT2-1.8B released?
Tencent (Hunyuan) released Hy-MT2-1.8B on 20 Aug 2026, according to OpenRouter.
How much VRAM does Hy-MT2-1.8B need?
About 2.6 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 3.5 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 |
|---|---|---|---|---|---|---|
| Tiny Aya Earth | Cohere | 17 Feb 2026 | 8K | – | – | Open |
| Tiny Aya Fire | Cohere | 17 Feb 2026 | 8K | – | – | Open |
| DeepSeek OCR 2 | DeepSeek | 27 Jan 2026 | 8K | $0.03 | $0.03 | Open |
| llama-nemotron-embed-vl-1b-v2 | NVIDIA | 18 Dec 2025 | 8K | – | – | Open |
| Reka Edge | Rekaai | 11 Mar 2026 | 16K | $0.10 | $0.10 | Open |
| llama-nemotron-rerank-vl-1b-v2 | NVIDIA | 18 Dec 2025 | 10K | – | – | Open |
Change history
- No longer listed on openrouter