← Back to community benchmarks
GLM-4.7-Flash
Performance
4k
tokens
446.8
PP tok/s
39.4
TG tok/s
9167
TTFT (ms)
24.3
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.2.8
macOS
macOS 15.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 490.1 | 48.0 | 23.3 GB | view |
| 4k | 446.8 | 39.4 | 24.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.0 | 1.00× |
| 2× | 61.0 | 1.27× |
| 4× | 67.9 | 1.41× |