← Back to community benchmarks
GLM-4.7-Flash
Performance
4k
tokens
734.6
PP tok/s
42.7
TG tok/s
5576
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
64 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 562.5 | 45.4 | 30.3 GB | view |
| 4k | 734.6 | 42.7 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.4 | 1.00× |
| 2× | 77.9 | 1.72× |
| 4× | 99.3 | 2.19× |