← Back to community benchmarks
GLM-4.7-Flash
Performance
16k
tokens
987.8
PP tok/s
40.0
TG tok/s
16587
TTFT (ms)
34.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.3.4
macOS
macOS 15.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,501 | 56.7 | 30.3 GB | view |
| 4k | 1,675 | 53.4 | 31.3 GB | view |
| 8k | 1,386 | 48.0 | 32.5 GB | view |
| 16k | 987.8 | 40.0 | 34.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.7 | 1.00× |
| 2× | 93.5 | 1.65× |
| 4× | 153.4 | 2.71× |
| 8× | 290.8 | 5.13× |