← Back to community benchmarks
GLM-4.7-Flash
Performance
1k
tokens
2,772
PP tok/s
71.5
TG tok/s
369
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.2rc2
macOS
macOS 26.5.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,772 | 71.5 | 30.3 GB | current |
| 4k | 2,474 | 60.7 | 31.3 GB | view |
| 8k | 1,925 | 56.2 | 32.5 GB | view |
| 16k | 1,282 | 50.6 | 34.9 GB | view |
| 32k | 729.7 | 44.4 | 39.9 GB | view |
| 64k | 413.5 | 35.8 | 50.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 71.5 | 1.00× |
| 2× | 108.7 | 1.52× |
| 4× | 152.1 | 2.13× |
| 8× | 315.3 | 4.41× |