← Back to community benchmarks
GLM-4.6V-Flash
Performance
4k
tokens
182.8
PP tok/s
17.7
TG tok/s
22412
TTFT (ms)
7.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 190.7 | 18.6 | 7.2 GB | view |
| 4k | 182.8 | 17.7 | 7.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.6 | 1.00× |
| 2× | 37.1 | 1.99× |
| 4× | 42.0 | 2.26× |