Yes — GLM 5.2 Air (106B) runs at 38 tok/s on M4 Ultra with 192 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.8s. A capable open-source LLM with 106B parameters.
LLMCheck measured GLM 5.2 Air on M4 Ultra using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.
| Metric | Value |
|---|---|
| Tokens per second | 38 tok/s |
| Time to first token | 0.8s |
| Quantization | Q4_K_M |
| Minimum RAM | 192 GB |
| Recommended engine | MLX |
| Parameters | 106B |
| Benchmark date | 2026-07 |
Q4_K_M 106B MLX M4 Ultra
The recommended engine for GLM 5.2 Air on M4 Ultra is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 34 tok/s | 0.9s | 128 GB | MLX |
| M5 Max | 30 tok/s | 1.1s | 64 GB | Ollama |
| M4 Max | 26 tok/s | 1.3s | 128 GB | MLX |
To run GLM 5.2 Air on M4 Ultra you need:
GLM 5.2 Air needs about 192 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
Not sure which Mac fits your budget? See the best Mac for running this →
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.
See how GLM 5.2 Air stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard