← Back to community benchmarks
GLM-4.7-Flash
Performance
8k
tokens
352.3
PP tok/s
37.3
TG tok/s
23256
TTFT (ms)
19.1
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
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 | 428.1 | 51.6 | 16.4 GB | view |
| 4k | 409.7 | 44.4 | 17.6 GB | view |
| 8k | 352.3 | 37.3 | 19.1 GB | current |
| 16k | 272.2 | 28.1 | 22.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.6 | 1.00× |
| 2× | 68.9 | 1.34× |
| 4× | 82.9 | 1.61× |
| 8× | 84.3 | 1.63× |