← Back to community benchmarks
GLM-4.7-Flash
Performance
32k
tokens
512.2
PP tok/s
31.4
TG tok/s
63970
TTFT (ms)
32.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,061 | 64.5 | 23.3 GB | view |
| 4k | 1,310 | 59.2 | 24.3 GB | view |
| 8k | 1,114 | 52.2 | 25.5 GB | view |
| 16k | 806.0 | 42.3 | 27.9 GB | view |
| 32k | 512.2 | 31.4 | 32.9 GB | current |
| 64k | 285.6 | 18.3 | 43.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.5 | 1.00× |
| 2× | 98.1 | 1.52× |
| 4× | 143.9 | 2.23× |
| 8× | 180.7 | 2.80× |