← Back to community benchmarks
GLM-4.7-Flash
Performance
8k
tokens
223.0
PP tok/s
23.2
TG tok/s
36728
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 337.7 | 37.0 | 16.3 GB | view |
| 4k | 278.5 | 30.5 | 17.4 GB | view |
| 8k | 223.0 | 23.2 | 18.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.0 | 1.00× |
| 2× | 46.2 | 1.25× |
| 4× | 51.4 | 1.39× |
| 8× | 54.4 | 1.47× |