Can the Apple M4 Max (48 GB) run MOSS-Image SFT?

Yes, but slowly

Slow. At FP16 it needs about 29.3 GB of 36.0 GB usable and takes about 82 s per image.

Best precision: FP16
Memory mode: Everything on GPU
Time per image: 82 s
Output: 1024×1024, 50 steps

Best app to run it on the Apple M4 Max (48 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 MOSS-Image SFT

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.

huggingface.co/unsloth/MOSS-Image-SFT-GGUF (opens in a new tab)

Original weights · Hugging Face

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

huggingface.co/OpenMOSS-Team/MOSS-Image-SFT (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/OpenMOSS/MOSS-Image (opens in a new tab)

git clone https://github.com/OpenMOSS/MOSS-Image

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (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 Slow: How well it runs on the Apple M4 Max (48 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.	36.9 / 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.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	5.2 / 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	82.1 / 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 M4 Max (48 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	29.3 GB	36.0 GB	82 s	Everything on GPU	Slow	82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	15.8 GB	36.0 GB	74 s	Everything on GPU	Slow	80Great quality (A) · 80 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.	Original weights (opens in a new tab)
`Q8 GGUF`	16.2 GB	36.0 GB	1.6 min	Everything on GPU	Slow	81Great quality (A) · 81 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4 GGUF`	13.8 GB	36.0 GB	1.6 min	Everything on GPU	Slow	76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)

Other hardware that runs it

80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 FP8 · 13 s · Runs great
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX FP8 · 14 s · Runs well
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 11 s · Runs great
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 FP8 · 24 s · Runs well
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 10 s · Runs great
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT FP16 · 20 s · Runs well (encoder in RAM)

Quick answers

How much memory does MOSS-Image SFT need on the M4 Max 48GB?

At FP16 it needs about 29.3 GB. The M4 Max 48GB has 36.0 GB usable.

How long does MOSS-Image SFT take on the M4 Max 48GB?

About 82 s 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.