← Back to community benchmarks
glm-4.7-flash-abliterated
Performance
4k
tokens
2,351
PP tok/s
65.0
TG tok/s
1742
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,077 | 70.6 | 30.3 GB | view |
| 4k | 2,351 | 65.0 | 31.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.6 | 1.00× |
| 2× | 111.5 | 1.58× |
| 4× | 152.3 | 2.16× |