← Back to community benchmarks
GLM-4.6V-Flash
Performance
32k
tokens
234.9
PP tok/s
16.2
TG tok/s
139480
TTFT (ms)
13.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
24 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 373.4 | 23.8 | 11.6 GB | view |
| 4k | 366.2 | 23.0 | 11.8 GB | view |
| 8k | 343.7 | 21.0 | 12.0 GB | view |
| 16k | 285.8 | 18.9 | 12.3 GB | view |
| 32k | 234.9 | 16.2 | 13.0 GB | current |
| 64k | 171.5 | 12.3 | 14.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.8 | 1.00× |
| 2× | 46.6 | 1.96× |
| 4× | 63.4 | 2.66× |
| 8× | 66.0 | 2.77× |