← Back to community benchmarks
GLM-4.7-Flash
Performance
4k
tokens
1,294
PP tok/s
44.4
TG tok/s
3166
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.20.dev1
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,325 | 50.0 | 30.3 GB | view |
| 4k | 1,294 | 44.4 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 50.0 | 1.00× |
| 2× | 70.2 | 1.40× |
| 4× | 89.1 | 1.78× |