← Back to community benchmarks
GLM-4.7-Flash
Performance
4k
tokens
917.2
PP tok/s
45.6
TG tok/s
4466
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.0
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 843.4 | 49.0 | 30.3 GB | view |
| 4k | 917.2 | 45.6 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.0 | 1.00× |
| 2× | 78.7 | 1.61× |
| 4× | 108.1 | 2.21× |
| 8× | 129.9 | 2.65× |