← Back to community benchmarks
GLM-4.7-Flash
Performance
4k
tokens
482.7
PP tok/s
34.7
TG tok/s
8486
TTFT (ms)
45.1
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 454.8 | 26.2 | 44.0 GB | view |
| 4k | 482.7 | 34.7 | 45.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.2 | 1.00× |
| 2× | 68.6 | 2.62× |
| 4× | 82.5 | 3.15× |