Tencent/Mixture of Experts

THunyuan-Large

Name: Hunyuan-Large
Author: Tencent

&nbspGITHUB&nbsp&nbsp | &nbsp&nbsp🖥️&nbsp&nbspofficial website&nbsp&nbsp｜&nbsp&nbsp🕖&nbsp&nbsp HunyuanAPI｜&nbsp&nbsp🐳&nbsp&nbsp Gitee

chatcodingreasoningmultilingualmath

389B

Parameters (52B active)

128K

Context length

Benchmarks

Quantizations

Architecture

MoE

Released

2024-11-05

Layers

KV Heads

Head Dim

128

Family

hunyuan

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	116.2 GB	low
IQ2_M	2.93	143.0 GB	low
Q2_K	3.16	154.1 GB	low
IQ3_XXS	3.25	158.5 GB	low
IQ3_XS	3.5	170.7 GB	low
Q3_K_S	3.64	177.5 GB	low
IQ3_M	3.76	183.3 GB	low
Q3_K_M	4	195.0 GB	low
Q3_K_L	4.3	209.6 GB	moderate
IQ4_XS	4.46	217.4 GB	moderate
Q4_K_S	4.67	227.6 GB	moderate
Q4_K_M	4.89	238.3 GB	good
Q5_K_S	5.57	271.3 GB	good
Q5_K_M	5.7	277.7 GB	good
Q6_K	6.56	319.5 GB	excellent
Q8_0	8.5	413.8 GB	lossless
FP16	16	778.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN HUNYUAN-LARGE NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (7)

HumanEval90.0

BBH89.5

IFEval85.0

MATH77.4

MBPP72.6

MMLU-PRO60.2

GPQA Diamond42.4

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run hunyuan:389b-q4_K_M

Tag may need adjustment — check ollama.com/library/hunyuan for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware