Can I run Hunyuan-A13B locally?

Yes, the weights are open and available on Hugging Face from Tencent, with FP8 and GPTQ-Int4 quantized variants to reduce memory requirements. That said, the full model has 80B total parameters, so you will need substantial hardware even with quantization.

What does it cost to use via API, and what is the context limit?

Tencent prices it at $0.14 per million input tokens and $0.57 per million output tokens through HunyuanAPI. The context window is 256K tokens natively.

How does Hunyuan-A13B differ from a standard 13B dense model?

It uses a Mixture-of-Experts architecture, so only 13B parameters are active per forward pass even though the full model holds 80B. This lets it match much larger dense models on benchmarks while keeping inference costs closer to a true 13B model.

Hunyuan A13B Instruct

2495°

#llm #tencent #reasoning #agents #coding #long context

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Tencent | 131,072 token context | $0.14/M input, $0.57/M output. 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 performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).

Guides for this model

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Hunyuan-A13B Instruct is a Mixture-of-Experts model from Tencent with 13B active parameters drawn from an 80B total, giving you dense-model quality at a fraction of the inference cost. It supports a 256K context window, chain-of-thought reasoning, and both fast and slow thinking modes. Open weights, quantization-ready, and priced cheaply via API, it suits developers who need a capable reasoning model without a large compute bill.

Known for

MoE efficiency: 13B active params from 80B total keeps inference lean
256K native context window for long-document and multi-turn work
Switchable fast and slow thinking modes for reasoning depth control
Strong agent benchmark results on BFCL-v3, τ-Bench and C3-Bench
Multiple quantization formats available: FP8, GPTQ-Int4 and more

Watch out for

80B total parameters means local deployment needs serious hardware despite the low active-param count.
Licence terms are not summarised here; check Tencent's published licence before any commercial use.
Benchmarks in the model card are evaluated on base models, not the instruct variant directly.

Best for

Prompts to try

Multi-step math proof

A train leaves city A at 08:00 travelling at 90 km/h. A second train leaves city B, 450 km away, at 09:30 travelling toward city A at 110 km/h. At what time do they meet, and how far from city A? Show each step of your reasoning before giving the final answer.

Agent tool-use plan

You are an agent with access to three tools: web_search(query), read_file(path), and send_email(to, subject, body). A user asks: 'Find the current EUR/USD rate, save it to rates.txt, then email it to finance@example.com with a one-sentence summary.' Write the exact sequence of tool calls you would make, with arguments, and explain why you order them that way.

Debug a concurrency bug

Here is a Python function that occasionally returns wrong results when called from multiple threads simultaneously. Identify the race condition, explain why it occurs, and rewrite the function to be thread-safe without using a global lock if possible: import threading counter = 0 def increment(n): global counter for _ in range(n): counter += 1

Compare with

Hy4 preview
Open-weights model
1,048,576 token context · $0.83/M input, $2.50/M output
Hy3
Open-weights model
262,144 token context · $0.13/M input, $0.53/M output
Hy3 preview
Open-weights model
262,144 token context · $0.18/M input, $0.60/M output
GPT-6 Luna
API-only model
1,050,000 token context · $0.10/M input, $0.50/M output

More text models from tencent

Questions people ask

Can I run Hunyuan-A13B locally?: Yes, the weights are open and available on Hugging Face from Tencent, with FP8 and GPTQ-Int4 quantized variants to reduce memory requirements. That said, the full model has 80B total parameters, so you will need substantial hardware even with quantization.
What does it cost to use via API, and what is the context limit?: Tencent prices it at $0.14 per million input tokens and $0.57 per million output tokens through HunyuanAPI. The context window is 256K tokens natively.
How does Hunyuan-A13B differ from a standard 13B dense model?: It uses a Mixture-of-Experts architecture, so only 13B parameters are active per forward pass even though the full model holds 80B. This lets it match much larger dense models on benchmarks while keeping inference costs closer to a true 13B model.

Captain's verdict
A well-priced open-weights MoE that punches above its active-parameter count, especially for agents and long-context reasoning.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

GPT 3.5 Turbo (older v0613)

TEXT / LLM

Qwen3.6 Flash

TEXT / LLM

AI Models for Image, Video & Text Generation

Hunyuan A13B Instruct is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm tencent reasoning agents coding long context local

Browse by Model Family