← Back to community benchmarks
GLM-4.7-Flash
Performance
1k
tokens
712.4
PP tok/s
41.5
TG tok/s
1437
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
128 GB
GPU Cores
64
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 712.4 | 41.5 | 30.3 GB | current |
| 4k | 749.3 | 38.6 | 31.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.5 | 1.00× |
| 2× | 66.3 | 1.60× |
| 4× | 100.7 | 2.43× |