← Back to community benchmarks
GLM-4.7-Flash
Performance
1k
tokens
1,107
PP tok/s
48.7
TG tok/s
925
TTFT (ms)
30.3
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
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,107 | 48.7 | 30.3 GB | current |
| 4k | 1,210 | 44.1 | 31.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.7 | 1.00× |
| 2× | 69.9 | 1.44× |
| 4× | 87.2 | 1.79× |