← Back to community benchmarks
GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill
Performance
8k
tokens
224.3
PP tok/s
24.6
TG tok/s
36526
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 | 335.8 | 37.4 | 16.3 GB | view |
| 4k | 280.0 | 29.8 | 17.4 GB | view |
| 8k | 224.3 | 24.6 | 18.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.4 | 1.00× |
| 2× | 46.4 | 1.24× |
| 4× | 50.7 | 1.36× |
| 8× | 54.2 | 1.45× |