← Back to community benchmarks
GLM-4.7-Flash
Performance
4k
tokens
1,078
PP tok/s
56.6
TG tok/s
3799
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,173 | 62.5 | 30.3 GB | view |
| 4k | 1,078 | 56.6 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.5 | 1.00× |
| 2× | 95.6 | 1.53× |
| 4× | 130.8 | 2.09× |