AuraFlow v0.3 on UP Squared Pro 7000 (16 GB)

Can the UP Squared Pro 7000 (16 GB) run AuraFlow v0.3?

Barely: it runs very slowly (tight fit)

Very slow (tight fit). At Q4 GGUF it needs about 7.7 GB of 8.0 GB usable and takes about 11.5 min per image.

Best precision: Q4 GGUF
Memory mode: Everything on GPU
Time per image: 11.5 min
Output: 1024×1024, 50 steps

Best app to run it on the UP Squared Pro 7000 (16 GB)

On Windows

ComfyUI

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

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

On Linux

ComfyUI

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

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Get ComfyUI

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 AuraFlow v0.3

Recommended for the UP Squared Pro 7000 (16 GB): q4_gguf. Every other precision has its own download link in the table below.

Quantized files · GGUF for ComfyUI

Smaller GGUF versions for ComfyUI (with the ComfyUI-GGUF node). No sign-in needed; the model’s license still applies.

Download the q4_gguf (Q4_K_S) file (opens in a new tab)

huggingface.co/city96/AuraFlow-v0.3-gguf (opens in a new tab)

Original weights · Hugging Face

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

huggingface.co/fal/AuraFlow-v0.3 (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 53Fair quality (C) · 53 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4 GGUF, 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 slowtight fit: How well it runs on the UP Squared Pro 7000 (16 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.	24.3 / 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.	23.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	1.8 / 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	64.1 / 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 UP Squared Pro 7000 (16 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	7.0 GB	8.0 GB	12.4 min	Sequential CPU offload	Very slowtight fit · CPU offload	58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	4.6 GB	8.0 GB	11.2 min	Sequential CPU offload	Very slowCPU offload	56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`Q8 GGUF`	4.8 GB	8.0 GB	14.3 min	Sequential CPU offload	Very slowCPU offload	57Good quality (B) · 57 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4 GGUF`	7.7 GB	8.0 GB	11.5 min	Everything on GPU	Very slowtight fit	53Fair quality (C) · 53 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)

Other hardware that runs it

56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT FP8 · 17 s · Runs well
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 FP8 · 17 s · Runs well
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER FP8 · 18 s · Runs well
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER FP8 · 20 s · Runs well
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti FP8 · 20 s · Runs well
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 FP16 · 26 s · Runs well

Quick answers

How much memory does AuraFlow v0.3 need on the UP Squared Pro 7000 16GB?

At Q4 GGUF it needs about 7.7 GB. The UP Squared Pro 7000 16GB has 8.0 GB usable.

How long does AuraFlow v0.3 take on the UP Squared Pro 7000 16GB?

About 11.5 min per image at Q4 GGUF 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.