← Back to community benchmarks
GLM-4.7-Flash
Performance
4k
tokens
503.0
PP tok/s
39.0
TG tok/s
8142
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
64 GB
GPU Cores
38
Software
oMLX
v0.2.8
macOS
macOS 15.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 520.0 | 43.7 | 30.3 GB | view |
| 4k | 503.0 | 39.0 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 43.7 | 1.00× |
| 2× | 68.5 | 1.57× |
| 4× | 90.7 | 2.08× |