Run GLM 5.2 on M3 Ultra

Yes — GLM 5.2 (753B-A40B) runs at 15 tok/s on M3 Ultra with 512 GB RAM using Q4_K_M quantization via MLX. First token latency is 2.0s. A capable open-source LLM with 753B-A40B parameters.

Speed
15
tok/s
First Token
2.0
seconds
RAM Needed
512
GB minimum
Engine
MLX
recommended
Want to run GLM 5.2 faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates GLM 5.2 on M3 Ultra using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →

MetricValue
Tokens per second15 tok/s
Time to first token2.0s
QuantizationQ4_K_M
Minimum RAM512 GB
Recommended engineMLX
Parameters753B-A40B
Benchmark date2026-07

Q4_K_M 753B-A40B MLX M3 Ultra

Setup Guide: Run GLM 5.2 on M3 Ultra

The recommended engine for GLM 5.2 on M3 Ultra is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/glm-52-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run glm-52

System Requirements

To run GLM 5.2 on M3 Ultra you need:

🛒 Get a Mac that runs GLM 5.2

GLM 5.2 needs about 512 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.

Compare More Models

See how GLM 5.2 stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard