Tencent (Hunyuan)

Hy-MT2-7B

Generally availableOpen weights8K context

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

DeveloperTencent (Hunyuan)
Release date21 May 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters8B [Hugging Face]
Context window8K (8,192 tokens) [models.dev]
Max output4K tokens [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]
Structured outputYes [models.dev]
Hugging Facetencent/Hy-MT2-7B [Hugging Face]

Hy-MT2-7B API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
tencent/hy-mt2-7b
$0.07$0.29–8KOpenRouter, 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.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)4.9 GB6.7 GB6.7 GB
Q8_0 (8-bit)8.5 GB10 GB10 GB
FP16 / BF16 (16-bit)16 GB18 GB18 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.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Reka EdgeRekaai11 Mar 202616K$0.10$0.10Open
DeepSeek OCR 2DeepSeek27 Jan 20268K$0.03$0.03Open
Tiny Aya EarthCohere17 Feb 20268K––Open
Tiny Aya FireCohere17 Feb 20268K––Open
Nemotron 3.5 Content SafetyNVIDIA2 Jun 2026131K$0.20$0.20Open
llama-nemotron-embed-vl-1b-v2NVIDIA18 Dec 20258K––Open

Change history

  • Release date changed from 19 Aug 2026 to 21 May 2026

Sources