← Back to community benchmarks
GLM-4.6V-Flash
Performance
4k
tokens
183.4
PP tok/s
17.3
TG tok/s
22329
TTFT (ms)
7.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 191.3 | 18.3 | 7.2 GB | view |
| 4k | 183.4 | 17.3 | 7.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.3 | 1.00× |
| 2× | 36.3 | 1.98× |
| 4× | 46.2 | 2.52× |