← Back to community benchmarks
GLM-4.5-Air
Performance
1k
tokens
378.2
PP tok/s
34.4
TG tok/s
2707
TTFT (ms)
81.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 378.2 | 34.4 | 81.9 GB | current |
| 4k | 375.9 | 30.8 | 82.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.4 | 1.00× |
| 2× | 44.6 | 1.30× |
| 4× | 48.1 | 1.40× |