LLMs · Zhipu AI

GLM-4.6 (355B-A32B)

Name: GLM-4.6 (355B-A32B)
Author: Zhipu AI

Parameters: 357B (32.0B active)
Architecture: Mixture of experts
Max context: 198K tokens
License: mit
Released: 2025-09

How to run it

Ollama

Ollama only offered this as a cloud model, and has since retired it. To run it locally, use the GGUF files below with llama.cpp or LM Studio.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/unsloth/GLM-4.6-GGUF (opens in a new tab)

ollama run hf.co/unsloth/GLM-4.6-GGUF

Original weights · Hugging Face

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

huggingface.co/zai-org/GLM-4.6 (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/GLM-4.5 (opens in a new tab)

git clone https://github.com/zai-org/GLM-4.5

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

Apps that run GLM-4.6 (355B-A32B)

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)

LM Studio

Runs the MLX build, typically up to 10% faster than GGUF for a model with 32B active parameters on Apple silicon.

Also good:

Windows PC, NVIDIA GPU

LM Studio

Point-and-click: search, download and chat in one window.

Also good:

Windows PC, AMD Radeon

Lemonade

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

Also good:

Linux, NVIDIA GPU

LM Studio

Point-and-click: search, download and chat in one window.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Ollama	CLI + API	GGUF from Hugging Face	macOSWindowsLinux	llama.cpp, MLX	`ollama run hf.co/unsloth/GLM-4.6-GGUF:Q4_K_M`
llama.cpp	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	`llama-server -hf unsloth/GLM-4.6-GGUF:Q4_K_M`
Jan	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX	Open in Jan
MLX LM	CLI + API	MLX	macOS	MLX	`mlx_lm.chat --model mlx-community/GLM-4.6-4bit`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve zai-org/GLM-4.6`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path zai-org/GLM-4.6`
Docker Model Runner	CLI + API	GGUF	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/unsloth/GLM-4.6-GGUF:Q4_K_M`
Lemonade	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, ONNX Runtime GenAI	`lemonade pull unsloth/GLM-4.6-GGUF:Q4_K_M`
Unsloth Desktop	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Open in Unsloth Desktop
Atomic Chat	Desktop app	GGUF or MLX	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
Pi	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp or MLX LM	Point it at a llama.cpp or MLX LM server
Hermes Agent	Assistant	GGUF or MLX	macOSWSLWindowsLinux	uses llama.cpp or MLX LM	Point it at a llama.cpp or MLX LM server
OpenClaw	Assistant	GGUF or MLX	macOSWSLWindowsLinux	uses llama.cpp or MLX LM	Point it at a llama.cpp or MLX LM server
OpenCode	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Codex CLI	Coding agent	GGUF or MLX	macOSWSLWindowsLinux	uses Ollama or any OpenAI-compatible server	Point it at a llama.cpp or MLX LM server
OpenHands	Coding agent	GGUF or MLX	macOSWSLWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Zed	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Cline	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Open Interpreter	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Goose	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Aider	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Crush	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Qwen Code	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Kilo Code	Coding agent	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Open WebUI	Assistant	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Khoj	Assistant	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
Letta	Assistant	GGUF or MLX	macOSWindowsLinux	uses llama.cpp, Ollama or LM Studio	Point it at a llama.cpp or MLX LM server
KoboldCpp	Desktop app	GGUF	macOSWindowsLinux	llama.cpp	Get KoboldCpp
Text Generation WebUI	Desktop app	GGUF	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI
llamafile	CLI + API	GGUF	macOSWindowsLinux	llama.cpp	Get llamafile
Msty Studio	Desktop app	GGUF or MLX	macOSWindowsLinux	Ollama, llama.cpp, MLX	Open in Msty Studio
Llama (macOS)	Desktop app	GGUF	macOS	llama.cpp	Open in Llama (macOS)
RecurseChat	Desktop app	GGUF	macOS	llama.cpp	Open in RecurseChat
Inferencer	Desktop app	MLX	macOS	MLX	Get Inferencer
node-llama-cpp	Library	GGUF	macOSWindowsLinux	llama.cpp	Get node-llama-cpp
exo	Server	MLX	macOSLinux	MLX	Get exo
Continue	Coding agent	GGUF or MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
SillyTavern	Assistant	GGUF or MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
LibreChat	Assistant	GGUF or MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
Cherry Studio	Assistant	GGUF or MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
Chatbox	Assistant	GGUF or MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
PrivateGPT	Assistant	GGUF or MLX	macOSWindowsLinux	uses Ollama, LM Studio or llama.cpp	Point it at a llama.cpp or MLX LM server
PocketPal AI	Mobile app	GGUF	iOSAndroid	llama.cpp	App Store Google Play
ChatterUI	Mobile app	GGUF	Android	llama.cpp	Download the APK
LLM Farm	Mobile app	GGUF	iOS	llama.cpp	Not on the App Store or TestFlight for now (checked 2026-11-09).

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

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	143 GB	146 GB	156 GB	GGUF · folder (opens in a new tab)
`Q3_K_M`	Low	175 GB	179 GB	188 GB	GGUF · folder (opens in a new tab)
`Q4_K_M`	Good	218 GB	221 GB	231 GB	GGUF · folder (opens in a new tab)
`Q5_K_M`	High	253 GB	257 GB	266 GB	GGUF · folder (opens in a new tab)
`Q6_K`	High	293 GB	296 GB	306 GB	GGUF · folder (opens in a new tab)
`Q8_0`	Very high	378 GB	382 GB	391 GB	GGUF · folder (opens in a new tab)
`F16`	Full	714 GB	717 GB	727 GB	GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for GLM-4.6 (355B-A32B)

Quality	Hardware	Quant	Memory	Speed	Runs
79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (512 GB)	`Q4_K_M`	252 GB / 384 GB	24.8 tok/s	Runs well
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (256 GB)	`Q2_K`	162 GB / 192 GB	39.0 tok/s	Runs great
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.	Apple M2 Ultra (192 GB)	`Q2_K`	158 GB / 144 GB	32.5 tok/s	Runs wellover GPU memory limit
79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI350X	`Q4_K_M`	236 GB / 288 GB	140 tok/s	Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	Apple M5 Ultra (512 GB)	`Q4_K_M`	252 GB / 384 GB	35.0 tok/s	Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI325X	`Q4_K_M`	234 GB / 256 GB	119 tok/s	Runs welltight fit
79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip	`Q4_K_M`	234 GB / 252 GB	142 tok/s	Runs welltight fit
70Great quality (A) · 70 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	AMD Instinct MI300X	`Q3_K_M`	188 GB / 192 GB	131 tok/s	Runs welltight fit
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Apple M5 Ultra (256 GB)	`Q2_K`	162 GB / 192 GB	54.1 tok/s	Runs great
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA B200	`Q2_K`	155 GB / 180 GB	196 tok/s	Runs welltight fit

Check it on your own hardware

Run it on a cluster

Devices that can’t run GLM-4.6 (355B-A32B) alone can run it together. These example clusters do:

Try it with your own devices

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.