← Back to community benchmarks
GLM-4.7-Flash
Performance
32k
tokens
639.0
PP tok/s
32.3
TG tok/s
51284
TTFT (ms)
39.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 938.0 | 68.8 | 30.3 GB | view |
| 4k | 2,120 | 64.9 | 31.3 GB | view |
| 8k | 1,884 | 56.7 | 32.5 GB | view |
| 16k | 1,244 | 46.2 | 34.9 GB | view |
| 32k | 639.0 | 32.3 | 39.8 GB | current |
| 64k | 330.3 | 21.7 | 50.0 GB | view |
| 128k | 162.2 | 12.6 | 70.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 68.8 | 1.00× |
| 2× | 103.1 | 1.50× |
| 4× | 131.8 | 1.92× |
| 8× | 157.9 | 2.30× |