tencent / text-to-image updated 6 months ago

HunyuanImage-3.0

Name: HunyuanImage-3.0
Author: tencent

- January 26, 2026: 🚀 HunyuanImage-3.0-Instruct-Distil - Distilled checkpoint for efficient deployment (8 steps sampling recommended). - January 26, 2026: 🎉 HunyuanImage-3.0-Instruct - Release of Instruct (with reasoning) for intelligent prompt enhancement and Image-to-Image generation for creative editing. - October 30, 2025: 🚀 HunyuanImage-3.0 vLLM Acceleration - Significantly faster inference with vLLM support....

Params

83.0 B

Context

22,800

Downloads 30d

16 K

Likes

1,103

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (6 recorded)

16 K downloads in the last 30 days

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	168.5 GB	198.3 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 22K ctx	168.5 GB	220.5 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: HunyuanImage3ForCausalMM
Parameters: 83.0 B
Tensor type: BF16
Context length: 22,800
Vocabulary: 133,120
Layers / heads: 32 / 32
Licence: other
First seen on the Hub: 2025-09-25
Training datasets: undisclosed
Added to our catalog: 2026-08-01

Compare with

stable-diffusion-v1-5 1.6 M stable-diffusion-xl-base-1.0 1.5 M sdxl-turbo 1.1 M dreamshaper-7 895 K Flux2-Klein-9B-True-V2 792 K sd-turbo 722 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB