Can the Apple M3 Max (96 GB) run CogVideoX 5B?

Yes, but slowly

Slow. At FP16 it needs about 24.1 GB of 72.0 GB usable and takes about 23.8 min per clip.

Best precision: FP16
Memory mode: Everything on GPU
Time per clip: 23.8 min
Output: 720×480, 49 frames, 50 steps

Best app to run it on the Apple M3 Max (96 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 CogVideoX 5B

Original weights · Hugging Face

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

huggingface.co/zai-org/CogVideoX-5b (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/zai-org/CogVideo (opens in a new tab)

git clone https://github.com/zai-org/CogVideo

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

How it’s rated

Quality 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (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 M3 Max (96 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.	24.8 / 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.	5.3 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	7.7 / 15
Match score	62.8 / 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 Max (96 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	24.1 GB	72.0 GB	23.8 min	Everything on GPU	Slow	55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	14.3 GB	72.0 GB	21.4 min	Everything on GPU	Slow	53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP16 · 2.5 min · Runs great
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 FP8 · 2.7 min · Runs great
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX FP8 · 3.0 min · Runs great
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT FP8 · 3.6 min · Runs well (tight fit)
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 FP8 · 3.6 min · Runs well (tight fit)
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER FP8 · 3.8 min · Runs well (tight fit)

Quick answers

How much memory does CogVideoX 5B need on the M3 Max 96GB?

At FP16 it needs about 24.1 GB. The M3 Max 96GB has 72.0 GB usable.

How long does CogVideoX 5B take on the M3 Max 96GB?

About 23.8 min per clip 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.