← Back to community benchmarks
GLM-4.7-Flash
Performance
32k
tokens
508.5
PP tok/s
31.6
TG tok/s
64438
TTFT (ms)
32.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,069 | 61.4 | 23.3 GB | view |
| 4k | 1,290 | 55.9 | 24.3 GB | view |
| 8k | 1,109 | 50.4 | 25.5 GB | view |
| 16k | 802.4 | 41.4 | 27.9 GB | view |
| 32k | 508.5 | 31.6 | 32.9 GB | current |
| 64k | 282.9 | 21.0 | 43.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.4 | 1.00× |
| 2× | 92.6 | 1.51× |
| 4× | 136.4 | 2.22× |
| 8× | 172.6 | 2.81× |