← Back to community benchmarks
GLM-4.7-Flash
Performance
4k
tokens
504.1
PP tok/s
39.2
TG tok/s
8126
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
64 GB
GPU Cores
38
Software
oMLX
v0.2.7
macOS
macOS 15.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 521.2 | 44.5 | 30.3 GB | view |
| 4k | 504.1 | 39.2 | 31.3 GB | current |
| 8k | 433.3 | 34.6 | 32.5 GB | view |
| 16k | 333.0 | 27.6 | 34.9 GB | view |
| 32k | 223.6 | 20.2 | 39.9 GB | view |
| 64k | 135.9 | 13.3 | 54.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.5 | 1.00× |
| 2× | 69.2 | 1.56× |
| 4× | 94.7 | 2.13× |
| 8× | 97.2 | 2.18× |