Can the Apple M3 (16 GB) run ERNIE-Image Turbo?

Yes, but slowly (encoder unloaded after use)

Slow (encoder unloaded after use). At Q4 GGUF it needs about 7.4 GB of 10.7 GB usable and takes about 73 s per image.

Best precision: Q4 GGUF
Memory mode: Text encoder offloaded
Time per image: 73 s
Output: 1024×1024, 8 steps

Best app to run it on the Apple M3 (16 GB)

On macOS

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 ERNIE-Image Turbo

Recommended for the Apple M3 (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/unsloth/ERNIE-Image-Turbo-GGUF (opens in a new tab)

Original weights · Hugging Face

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

huggingface.co/baidu/ERNIE-Image-Turbo (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/baidu/ERNIE-Image (opens in a new tab)

git clone https://github.com/baidu/ERNIE-Image

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

How it’s rated

Quality 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (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 Slowencoder unloaded after use: How well it runs on the Apple M3 (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.	35.6 / 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.	20.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	5.6 / 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	76.1 / 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 Apple M3 (16 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	8.1 GB	10.7 GB	75 s	Sequential CPU offload	SlowCPU offload	85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	5.2 GB	10.7 GB	68 s	Sequential CPU offload	SlowCPU offload	83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`Q8 GGUF`	5.4 GB	10.7 GB	86 s	Sequential CPU offload	SlowCPU offload	84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4 GGUF`	7.4 GB	10.7 GB	73 s	Text encoder offloaded	Slowencoder unloaded after use	79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)

Other hardware that runs it

85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP16 · 2.7 s · Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q8 GGUF · 4.1 s · Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8 GGUF · 6.9 s · Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8 GGUF · 3.7 s · Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8 GGUF · 4.9 s · Runs well (tight fit)
84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Ti 16GB Q8 GGUF · 9.9 s · Runs well (tight fit)

Quick answers

How much memory does ERNIE-Image Turbo need on the M3 16GB?

At Q4 GGUF it needs about 7.4 GB. The M3 16GB has 10.7 GB usable.

How long does ERNIE-Image Turbo take on the M3 16GB?

About 73 s 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.