← Back to community benchmarks
GLM-4.7-Flash
Performance
4k
tokens
511.3
PP tok/s
42.6
TG tok/s
8010
TTFT (ms)
24.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.14
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 546.1 | 49.1 | 23.3 GB | view |
| 4k | 511.3 | 42.6 | 24.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.1 | 1.00× |
| 2× | 71.1 | 1.45× |
| 4× | 86.8 | 1.77× |