← Back to community benchmarks

GLM-4-9B-0414

M1 Pro (14c) · 16 GB · 4bit · 2026-03-10
Performance
1k
tokens
195.1
PP tok/s
29.0
TG tok/s
5249
TTFT (ms)
5.8
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 195.1 29.0 5.8 GB current
4k 182.4 25.7 5.9 GB view
16k 152.0 18.1 6.4 GB view
Batching Results
Batch Size TG tok/s Speedup
29.0 1.00×
36.2 1.25×
37.5 1.29×