← Back to community benchmarks
GLM-4.7-Flash
Performance
1k
tokens
1,007
PP tok/s
63.0
TG tok/s
1017
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,007 | 63.0 | 30.3 GB | current |
| 4k | 1,088 | 57.7 | 31.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.0 | 1.00× |
| 2× | 103.2 | 1.64× |
| 4× | 138.5 | 2.20× |