← Back to community benchmarks
GLM-4.7-Flash-oQ6
Performance
32k
tokens
678.9
PP tok/s
34.8
TG tok/s
48268
TTFT (ms)
33.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,250 | 74.8 | 23.6 GB | view |
| 4k | 2,197 | 67.6 | 24.6 GB | view |
| 8k | 1,917 | 59.7 | 25.8 GB | view |
| 16k | 1,231 | 47.6 | 28.2 GB | view |
| 32k | 678.9 | 34.8 | 33.2 GB | current |
| 64k | 247.8 | 16.7 | 43.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 74.8 | 1.00× |
| 2× | 91.3 | 1.22× |
| 4× | 105.4 | 1.41× |