Can the Apple M1 Pro (16 GB) run CogView4 6B?

Barely: it runs very slowly (encoder unloaded after use)

Very slow (encoder unloaded after use). At FP8 it needs about 8.8 GB of 10.7 GB usable and takes about 4.3 min per image.

Best precision: FP8
Memory mode: Text encoder offloaded
Time per image: 4.3 min
Output: 1024×1024, 50 steps

Best app to run it on the Apple M1 Pro (16 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 CogView4 6B

Original weights · Hugging Face

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

huggingface.co/zai-org/CogView4-6B (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/CogView4 (opens in a new tab)

git clone https://github.com/zai-org/CogView4

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (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 Very slowencoder unloaded after use: How well it runs on the Apple M1 Pro (16 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.	30.9 / 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.	20.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	3.0 / 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	68.8 / 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 M1 Pro (16 GB)

Quant	Memory needed	Available	Speed	Memory mode	Runs	Quality	Download
`FP16`	6.7 GB	10.7 GB	5.9 min	Sequential CPU offload	Very slowCPU offload	70Great quality (A) · 70 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.	Original weights (opens in a new tab)
`FP8`	8.8 GB	10.7 GB	4.3 min	Text encoder offloaded	Very slowencoder unloaded after use	68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Other hardware that runs it

68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 FP8 · 16 s · Runs well
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX FP8 · 18 s · Runs well
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 FP8 · 14 s · Runs well
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 FP8 · 30 s · Runs well
68Good quality (B) · 68 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 SUPER FP8 · 32 s · Runs well (encoder in RAM)
68Good quality (B) · 68 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 RTX PRO 6000 Blackwell FP8 · 12 s · Runs great

Quick answers

How much memory does CogView4 6B need on the M1 Pro 16GB?

At FP8 it needs about 8.8 GB. The M1 Pro 16GB has 10.7 GB usable.

How long does CogView4 6B take on the M1 Pro 16GB?

About 4.3 min per image 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.