← Back to community benchmarks
GLM-4.5-Air
Performance
1k
tokens
889.9
PP tok/s
39.6
TG tok/s
1151
TTFT (ms)
81.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 889.9 | 39.6 | 81.9 GB | current |
| 4k | 997.7 | 33.6 | 82.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.6 | 1.00× |
| 2× | 48.1 | 1.21× |
| 4× | 53.8 | 1.36× |