← Back to community benchmarks
GLM-4.7-Flash
Performance
8k
tokens
456.3
PP tok/s
40.8
TG tok/s
17952
TTFT (ms)
19.1
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 605.6 | 59.8 | 16.4 GB | view |
| 4k | 559.7 | 49.3 | 17.6 GB | view |
| 8k | 456.3 | 40.8 | 19.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 59.8 | 1.00× |
| 2× | 85.0 | 1.42× |
| 4× | 101.6 | 1.70× |
| 8× | 110.4 | 1.85× |