← Back to community benchmarks
GLM-4.7-Flash
Performance
1k
tokens
1,351
PP tok/s
54.7
TG tok/s
758
TTFT (ms)
256.6
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.12
macOS
macOS 15.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,351 | 54.7 | 256.6 GB | current |
| 4k | 1,595 | 52.1 | 257.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.7 | 1.00× |
| 2× | 91.1 | 1.67× |
| 4× | 148.4 | 2.71× |