Hy-MT2-7B
Summary
Hy-MT2-7B is an open-weight language model from Tencent (Hunyuan), released on 21 May 2026. It accepts text and generates text, with a 8K-token context window and up to 4K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.07 per million input tokens and $0.29 per million output tokens (OpenRouter), across 1 provider we track.
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Tencent (Hunyuan) |
|---|---|
| Release date | 21 May 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 8B [Hugging Face] |
| Context window | 8K (8,192 tokens) [models.dev] |
| Max output | 4K tokens [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | tencent/Hy-MT2-7B [Hugging Face] |
Hy-MT2-7B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter tencent/hy-mt2-7b | $0.07 | $0.29 | – | 8K | OpenRouter, 18 Nov 2026 |
Running Hy-MT2-7B 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) | 4.9 GB | 6.7 GB | 6.7 GB |
| Q8_0 (8-bit) | 8.5 GB | 10 GB | 10 GB |
| FP16 / BF16 (16-bit) | 16 GB | 18 GB | 18 GB |
At 4-bit with an 8K conversation, Hy-MT2-7B needs about 6.7 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-MT2-7B?
Hy-MT2-7B has a context window of 8,192 tokens (8K) and can generate up to 4,096 tokens in a single response, according to models.dev.
How much does the Hy-MT2-7B API cost?
Hy-MT2-7B is listed from $0.07 per million input tokens and $0.29 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.
Is Hy-MT2-7B open source?
Hy-MT2-7B is an open-weight model: its weights are published on Hugging Face as tencent/Hy-MT2-7B under the apache-2.0 license. Check the license terms before commercial use.
When was Hy-MT2-7B released?
Tencent (Hunyuan) released Hy-MT2-7B on 21 May 2026, according to models.dev.
How much VRAM does Hy-MT2-7B need?
About 6.7 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 10 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 |
|---|---|---|---|---|---|---|
| Reka Edge | Rekaai | 11 Mar 2026 | 16K | $0.10 | $0.10 | Open |
| DeepSeek OCR 2 | DeepSeek | 27 Jan 2026 | 8K | $0.03 | $0.03 | Open |
| Tiny Aya Earth | Cohere | 17 Feb 2026 | 8K | – | – | Open |
| Tiny Aya Fire | Cohere | 17 Feb 2026 | 8K | – | – | Open |
| Nemotron 3.5 Content Safety | NVIDIA | 2 Jun 2026 | 131K | $0.20 | $0.20 | Open |
| llama-nemotron-embed-vl-1b-v2 | NVIDIA | 18 Dec 2025 | 8K | – | – | Open |
Change history
- Release date changed from 19 Aug 2026 to 21 May 2026