Image models · Zhipu AI

CogView4 6B

Name: CogView4 6B
Author: Zhipu AI

Backbone: 6.4B
Native output: 1024×1024
Default steps: 50
License: apache-2.0
Released: 2025-03

How to run it

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.

Apps that run CogView4 6B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Windows PC, NVIDIA GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Linux, NVIDIA or AMD GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

App	Type	Opens it as	Systems	Engine	Start
ComfyUI	Desktop app	Built-in support	macOSWindowsLinux	PyTorch, GGUF via ComfyUI-GGUF	Get ComfyUI
Invoke	Desktop app	Built-in support	macOSWindowsLinux	PyTorch	Get Invoke
SwarmUI	Desktop app	Built-in support	macOSWindowsLinux	ComfyUI	Get SwarmUI
SD.Next	Desktop app	Built-in support	macOSWindowsLinux	PyTorch	Get SD.Next
Stability Matrix	Desktop app	Built-in support	macOSWindowsLinux	installs ComfyUI, Forge, InvokeAI, SwarmUI, SD.Next or Fooocus	Get Stability Matrix

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision	Everything on GPU	Text encoder offloaded	Sequential offload	Download
`FP16`	33.9 GB	15.1 GB	6.7 GB	Original weights (opens in a new tab)
`FP8`	18.2 GB	8.8 GB	4.4 GB	Original weights (opens in a new tab)

Components

Backbone: 6.37B
VAE: 0.084B
GLM-4 9B: 9.4B

Best hardware for CogView4 6B

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at FP8.

Quality	Hardware	Quant	Memory	Speed	Runs
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`	18.2 GB / 24.0 GB	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`	18.2 GB / 24.0 GB	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`	18.2 GB / 32.0 GB	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`	18.2 GB / 24.0 GB	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`	8.8 GB / 12.0 GB	32 s	Runs wellencoder 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`	18.2 GB / 96.0 GB	12 s	Runs great
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`FP8`	8.8 GB / 16.0 GB	23 s	Runs wellencoder in RAM
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5080	`FP8`	8.8 GB / 16.0 GB	23 s	Runs wellencoder in RAM
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4080 SUPER	`FP8`	8.8 GB / 16.0 GB	24 s	Runs wellencoder in RAM
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max+ 395 (128 GB)	`FP16`	33.9 GB / 96.0 GB	35 s	Runs well

Check it on your own hardware

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.