← Back to community benchmarks
GLM-4.7-Flash-oQ8
Performance
16k
tokens
403.7
PP tok/s
28.3
TG tok/s
40590
TTFT (ms)
35.9
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
64 GB
GPU Cores
30
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 699.6 | 42.8 | 30.3 GB | view |
| 4k | 685.0 | 37.9 | 31.3 GB | view |
| 8k | 564.8 | 33.7 | 32.5 GB | view |
| 16k | 403.7 | 28.3 | 35.9 GB | current |
| 32k | 252.2 | 21.0 | 42.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.8 | 1.00× |
| 2× | 60.9 | 1.42× |
| 4× | 82.5 | 1.93× |