Can the UDOO BOLT V8 (8 GB) run Hunyuan-DiT v1.2?

Barely: it runs very slowly (CPU offload)

Very slow (CPU offload). At FP16 it needs about 3.1 GB of 4.0 GB usable and takes about 2.9 min per image.

Best precision: FP16
Memory mode: Sequential CPU offload
Time per image: 2.9 min
Output: 1024×1024, 50 steps

Best app to run it on the UDOO BOLT V8 (8 GB)

On Windows

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Can only use the CPU on this hardware, so it will be slow.
Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

SwarmUI Can only use the CPU on this hardware, so it will be slow.
SD.Next Can only use the CPU on this hardware, so it will be slow.

On Linux

ComfyUI

Desktop app · runs on PyTorch (ComfyUI), GGUF via ComfyUI-GGUF

Can only use the CPU on this hardware, so it will be slow.
Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

SwarmUI Can only use the CPU on this hardware, so it will be slow.
SD.Next Can only use the CPU on this hardware, so it will be slow.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Hunyuan-DiT v1.2

Original weights · Hugging Face

Full-precision files from Tencent, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Tencent. The weights themselves download from Hugging Face.

github.com/Tencent-Hunyuan/HunyuanDiT (opens in a new tab)

git clone https://github.com/Tencent-Hunyuan/HunyuanDiT

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP16, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Very slowCPU offload: How well it runs on the UDOO BOLT V8 (8 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	23.4 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	12.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	3.6 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	54.0 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every precision on the UDOO BOLT V8 (8 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	3.1 GB	4.0 GB	2.9 min	Sequential CPU offload	Very slowCPU offload	52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 SUPER FP16 · 11 s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT FP16 · 8.0 s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER FP16 · 9.6 s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER FP16 · 8.5 s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti FP16 · 9.6 s · Runs great
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 FP16 · 8.0 s · Runs great

Quick answers

How much memory does Hunyuan-DiT v1.2 need on the UDOO BOLT V8 8GB?

At FP16 it needs about 3.1 GB. The UDOO BOLT V8 8GB has 4.0 GB usable.

How long does Hunyuan-DiT v1.2 take on the UDOO BOLT V8 8GB?

About 2.9 min per image at FP16 and default settings, an estimate scaled from a reference timing by this hardware’s compute speed.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.