← Back to community benchmarks
GLM-4.7-Flash
Performance
1k
tokens
608.4
PP tok/s
49.8
TG tok/s
1683
TTFT (ms)
23.3
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 608.4 | 49.8 | 23.3 GB | current |
| 4k | 546.4 | 42.5 | 24.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.8 | 1.00× |
| 2× | 67.0 | 1.35× |
| 4× | 76.1 | 1.53× |
| 8× | 85.2 | 1.71× |