Cosmos 1.0 Diffusion 7B Text2World on Apple M4 (24 GB)

Can the Apple M4 (24 GB) run Cosmos 1.0 Diffusion 7B Text2World?

No, it doesn’t fit

No. Cosmos 1.0 Diffusion 7B Text2World needs about 29.2 GB even at FP16; the Apple M4 (24 GB) has 16.1 GB usable.

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 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 8/100 (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 Won't run: How well it runs on the Apple M4 (24 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.	8.1 / 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.	0.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	0.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	0.0 / 15
Match score	8.1 / 100

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

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Every precision on the Apple M4 (24 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	29.2 GB	16.1 GB	—	—	Won't run	60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Hardware that can run it

60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell FP16 · 6.7 min · Runs well
60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP16 · 10.0 min · Runs well (tight fit · CPU offload)
60Good quality (B) · 60 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 H100 80GB SXM FP16 · 6.4 min · Runs well
60Good quality (B) · 60 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 H800 80GB SXM FP16 · 6.4 min · Runs well
60Good quality (B) · 60 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 H100 80GB PCIe FP16 · 7.8 min · Runs well
60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 5000 Blackwell 72GB FP16 · 11.0 min · Runs well

Models that do run on the Apple M4 (24 GB)

49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. LTX-Video 2B FP8 · 6.5 min
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. Wan 2.1 T2V 1.3B FP8 · 62.8 min
44Fair quality (C) · 44 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. CogVideoX 2B FP8 · 15.7 min
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Kandinsky 6.0 Video Lite (3B, video + audio) FP16 · 1.6 h
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. Bernini-R A14B (video generation + editing) FP8 · 4.1 h

Quick answers

How much memory does Cosmos 1.0 Diffusion 7B Text2World need on the M4 24GB?

Even at FP16 it needs about 29.2 GB; the M4 24GB has 16.1 GB usable.

What can the M4 24GB run instead?

LTX-Video 2B, Wan 2.1 T2V 1.3B and CogVideoX 2B run best on it; the page lists more, each with its speed.

What hardware can run Cosmos 1.0 Diffusion 7B Text2World?

NVIDIA RTX PRO 6000 Blackwell 96GB, RTX 5090 32GB and NVIDIA H100 80GB SXM run it; the page lists more, each with its 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.