← Back to community benchmarks

GLM-4-9B-0414

M1 Pro (14c) · 16 GB · 4bit · 2026-03-10
Performance
16k
tokens
152.0
PP tok/s
18.1
TG tok/s
107771
TTFT (ms)
6.4
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 16 GB
GPU Cores 14
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 195.1 29.0 5.8 GB view
4k 182.4 25.7 5.9 GB view
16k 152.0 18.1 6.4 GB current
Batching Results
Batch Size TG tok/s Speedup
29.0 1.00×
36.2 1.25×
37.5 1.29×