Can the Apple M2 (8 GB) run CogVideoX 2B?

Yes, but slowly (tight fit · CPU offload)

Slow (tight fit · CPU offload). At FP8 it needs about 4.7 GB of 5.4 GB usable and takes about 23.3 min per clip.

Best precision: FP8
Memory mode: Sequential CPU offload
Time per clip: 23.3 min
Output: 720×480, 49 frames, 50 steps

Best app to run it on the Apple M2 (8 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 2B

Original weights · Hugging Face

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

huggingface.co/zai-org/CogVideoX-2b (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 1 day ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at FP8, 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 Slowtight fit · CPU offload: How well it runs on the Apple M2 (8 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.	19.8 / 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.	10.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	5.4 / 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	50.2 / 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 M2 (8 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	5.3 GB	5.4 GB	—	—	Won't run	45Fair quality (C) · 45 of 100: how capable the model is at FP16, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`FP8`	4.7 GB	5.4 GB	23.3 min	Sequential CPU offload	Slowtight fit · CPU offload	44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

45Fair quality (C) · 45 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. AMD Radeon RX 7900 XTX FP16 · 67 s · Runs great
45Fair quality (C) · 45 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 GeForce RTX 3090 FP16 · 1.9 min · Runs great
45Fair quality (C) · 45 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 GeForce RTX 4090 FP16 · 60 s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT FP8 · 72 s · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4060 Ti 16GB FP8 · 2.4 min · Runs great
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER FP8 · 86 s · Runs great

Quick answers

How much memory does CogVideoX 2B need on the M2 8GB?

At FP8 it needs about 4.7 GB. The M2 8GB has 5.4 GB usable.

How long does CogVideoX 2B take on the M2 8GB?

About 23.3 min per clip at FP8 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.