← Back to community benchmarks

GLM-4.7-Flash

M4 Max (40c) · 128 GB · 8bit · 2026-04-12
Performance
16k
tokens
650.0
PP tok/s
41.7
TG tok/s
25206
TTFT (ms)
35.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,071 62.7 30.3 GB view
4k 1,090 57.6 31.3 GB view
8k 896.0 50.3 32.8 GB view
16k 650.0 41.7 35.9 GB current
Batching Results
Batch Size TG tok/s Speedup
62.7 1.00×
96.9 1.55×