OpenModelsHQ

Hunyuan-A13B-Instruct

Tencent HunyuanLLMMoECustom licenseChina Desk

Hunyuan-A13B-Instruct is an open-weight language model from Tencent Hunyuan with 80.4B parameters (mixture of experts). At 4-bit it needs about 54.2 GB of memory, so the smallest current device that fits it is the A100 80GB SXM.

Overview

Estimated memory at 4-bit
54.2GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
80.4B
Mixture of experts, all weights counted
Context window
32K
32,768 tokens
Cheapest API, blended / 1M
$0.2475
₹23 · SiliconFlow · 3:1 input to output
All Tencent Hunyuan API prices

Key information

Lab
Tencent Hunyuan
Released
25 Jun 2025
Parameters
80.4B · MoE
Type
Language
Context
32,768 tokens
HF downloads, 30 days
70,361
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
Hunyuan-A13B-Instruct needs about 54.2 GB at 4-bit, 94.9 GB at 8-bit and 178 GB at 16-bit. At 4-bit it fits DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q454.2 GB
Q894.9 GB
BF16178 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 54.2 GBToo big 151%A100 80GB SXM80 GB memory
8-bit (Q8)≈ 94.9 GBToo big 264%DGX Spark128 GB memory
16-bit (BF16)≈ 178 GBToo big 494%RubinAnnounced288 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

Start with the MLX files, built for Apple Silicon.

mlx-community/Hunyuan-A13B-Instruct-4bitCheck your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

unsloth/Hunyuan-A13B-Instruct-GGUFFind compatible hardware

Through an API

SiliconFlow (fp8) is the cheapest provider we found.

$0.14 / $0.57

Input / output per 1M tokens
₹13 / ₹54 at ₹94.29 per $1

Blended: $0.2475 (₹23) per 1M. Ranked by a 3:1 mix of input and output tokens.

MLX on Apple SiliconView repository
mlx_lm.generate --model mlx-community/Hunyuan-A13B-Instruct-4bit \
  --prompt "Explain how a transformer works."
GGUF with llama.cppView repository
llama-cli -hf unsloth/Hunyuan-A13B-Instruct-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of MLX or llama.cpp. We have not run them; check each repository for available files.

Hosted API 1

USD and INR per million tokensAll Tencent Hunyuan API prices
Precision
SiliconFlowCheapest$0.2475₹23$0.14₹13$0.57₹54131,072FP8
View on OpenRouterEndpoint sourceSorted by the blended price: 3 parts input to 1 part output. Context limits differ by provider.

INR at ₹94.29 per $1. Prices fetched 14 Nov 2026.

More about this model

Frequently asked questions

How much memory does Hunyuan-A13B-Instruct need? At an 8k context, about 54.2 GB at 4-bit, 94.9 GB at 8-bit and 178 GB at 16-bit (BF16). A longer context needs more.

Can I run Hunyuan-A13B-Instruct on a Mac? The smallest current Mac that fits the 4-bit estimate of 54.2 GB is the Mac Studio M5 Ultra (96GB). An MLX build is available: mlx-community/Hunyuan-A13B-Instruct-4bit.

Does the full context fit? Hunyuan-A13B-Instruct supports up to 32,768 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? The cheapest provider we found is SiliconFlow, at $0.14 per 1M input tokens and $0.57 per 1M output tokens (₹13 and ₹54 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

License in plain English

Custom license. This model uses a custom license rather than a standard one. Read it on the model card before using the model commercially. This summary is not legal advice.

Read the license on the model card

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources