Cosmos 1.0 Diffusion 7B Text2World on Apple M4 Max (128 GB)

Can the Apple M4 Max (128 GB) run Cosmos 1.0 Diffusion 7B Text2World?

67 pts

Yes, it runs well

Runs well. At FP16 it needs about 48.2 GB of 96.0 GB usable, with an estimated speed of 53.7 min.

Best precision: FP16
Memory mode: Everything on GPU
Time per clip: 53.7 min
Output: 1280×704, 121 frames, 35 steps

Download Cosmos 1.0 Diffusion 7B Text2World

Original weights · Hugging Face

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

huggingface.co/nvidia/Cosmos-1.0-Diffusion-7B-Text2World (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Official repo · GitHub

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

github.com/nvidia-cosmos/cosmos-predict1 (opens in a new tab)

git clone https://github.com/nvidia-cosmos/cosmos-predict1

Links checked 1 week ago against Hugging Face, Ollama and GitHub.

How the B grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	27.0 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	3.5 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	11.6 / 15
Total	67.1 / 100	67 ptsGood (B) · 67 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 3.5/15, Memory use 11.6/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every precision on the Apple M4 Max (128 GB)

Precision	Memory needed	Available	Time per output	Memory mode	Fit	Grade · points	Download
`FP16`	48.2 GB	96.0 GB	53.7 min	Everything on GPU	Runs well	67 ptsGood (B) · 67 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 3.5/15, Memory use 11.6/15	Original weights (opens in a new tab)

Other hardware that runs it

73 ptsGreat (A) · 73 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 10.0/15, Memory use 11.6/15 NVIDIA RTX PRO 6000 Blackwell FP16 · 6.7 min
69 ptsGood (B) · 69 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 6.2/15, Memory use 11.6/15 AMD Ryzen AI Max+ 395 (128 GB) FP16 · 17.6 min
67 ptsGood (B) · 67 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 5.9/15, Memory use 9.7/15 NVIDIA GB10 (128 GB) FP16 · 19.1 min
65 ptsGood (B) · 65 of 100 points: Model quality 27.0/45, Memory fit 20.0/25, Speed 3.5/15, Memory use 15.0/15 Apple M4 Max (64 GB) FP16 · 56.4 min
64 ptsGood (B) · 64 of 100 points: Model quality 27.0/45, Memory fit 20.0/25, Speed 2.8/15, Memory use 15.0/15 Apple M1 Max (64 GB) FP16 · 86.5 min

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.