← Back to community benchmarks
GLM-4.7-Flash
Performance
8k
tokens
658.5
PP tok/s
39.9
TG tok/s
12441
TTFT (ms)
25.5
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
64 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 570.8 | 50.7 | 23.3 GB | view |
| 4k | 726.3 | 44.7 | 24.3 GB | view |
| 8k | 658.5 | 39.9 | 25.5 GB | current |
| 16k | 513.7 | 31.7 | 27.9 GB | view |
| 32k | 351.1 | 24.0 | 32.9 GB | view |
| 64k | 195.2 | 15.8 | 43.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 50.7 | 1.00× |
| 2× | 75.0 | 1.48× |
| 4× | 107.7 | 2.12× |
| 8× | 127.5 | 2.51× |