← Back to community benchmarks
GLM-4.7-Flash
Performance
1k
tokens
1,654
PP tok/s
54.8
TG tok/s
619
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,654 | 54.8 | 30.3 GB | current |
| 4k | 1,683 | 52.3 | 31.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.8 | 1.00× |
| 2× | 90.2 | 1.65× |
| 4× | 148.5 | 2.71× |