← Back to community benchmarks
GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill
Performance
4k
tokens
232.3
PP tok/s
26.8
TG tok/s
17632
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 272.6 | 33.8 | 15.4 GB | view |
| 4k | 232.3 | 26.8 | 16.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 33.8 | 1.00× |
| 2× | 41.1 | 1.22× |
| 4× | 44.2 | 1.31× |